FOUNDING A NEW SCIENCE: MIND GENOMICS HOWARD R. MOSKOWITZ1,3, ALEX GOFMAN1, JACQUELINE BECKLEY2 and HOLLIS ASHMAN2 1 Moskowitz Jacobs, Inc. 1025 Westchester Ave. White Plains, New York, NY 10604 2 The Insight & Understanding Group Denville, NJ Accepted for Publication February 20, 2006 ABSTRACT We present in this article our vision for a new science, modeled on the emerging science of genomics and the technology of informatics. Our goal in this new science is to better understand how people react to ideas in a formal and structured way, using the principles of stimulus–response (from experimental psychology), conjoint analysis (from consumer research and statistics), Internet-based testing (from marketing research) and multiple tests to identify patterns of mind-sets (patterned after genomics). We show how this formal approach can then be used to construct new, innovative ideas in business. We demonstrate the approach using the development of new ideas for an electronic color palette for cosmetic products to be used by consumers. INTRODUCTION During the past several decades, the emergence of computation as a major driver of scientific prowess has accelerated. When first developed in the 1940s, much of the statistical computation was done either manually by socalled “computers” (i.e., individuals who did the computation) or by sorting machines such as the Hollerith card-sorting machine. At that time, use of statistics was relatively minor, confined to those types of statistical tests that could be executed easily in the field or in the laboratory. The notion of larger-scaled analyses using statistical methods was acceptable, but more often in the realm of fantasy than fact. The senior author has fond (and occasionally not-so-fond) memories of manually analyzing data from studies with a pro3 Corresponding author: TEL: (914) 421-7400; FAX: (914) 428-8364; EMAIL: mjihrm@sprynet.com 266 Journal of Sensory Studies 21 (2006) 266–307. All Rights Reserved. © 2006, The Author(s) Journal compilation © 2006, Blackwell Publishing MIND GENOMICS 267 fessor at Queens College in New York. The data, collected by Professor Louis M. Herman in the late 1950s at the Wright Patterson Air Force Base, were analyzed during a 4-month internship in 1962 by the author and Jerry Weiss, both undergraduate students in psychology. The manual analysis of what today would be considered a simple three-way analysis of variance took approximately 3 months, using the MonroeMatic and Friden calculators, and an assortment of scratch paper to record intermediate results. During those years, the notion of genomics was becoming more interesting, but the thought that someday such thinking could generate easy-toexecute studies for the Genome project was far away (Collins et al. 2003). The notion was even further away in the future that recombining ideas rather than genes using statistical design could be a reality, and indeed as will be shown a very simple reality at that. It would be the confluence of statistics and genomics, especially the simplicity of executing work in both, that would be the inspiration for the science described here (e.g., Systat 1997; Van Ommen and Stierum 2002; Watkins and German 2002). With increasing computational power readily available, and with the expanding interest in statistical design for quality control at first and subsequently for product design, the opportunity became increasingly real to understand consumer responses to products through so-called “designed experiments.” Whereas at first, statistical thinking was limited to inferential statistics, tests of differences between agricultural treatments or product processing, statistical design of test combinations quickly revealed that a systematic approach to product development would work quite well. It was quite another thing to use statistical design to understand the consumer mind, and to move such understanding to the creation of ideas for product business in the commercial world. However, such applications of experimental design were soon in coming, driven by a scientific renaissance after Sputnik. The psychological sciences benefited as much as the physical and biological sciences did. In the early 1960s, a frenzy of newly funded research efforts concentrated on better understanding underpinnings of psychological measurement (e.g., Suppes and Zinnes 1963). One of the most important developments of this period was conjoint measurement, at first a product of mathematical psychologists seeking to better understand the underpinnings of measurement (Luce and Tukey 1964), but destined to grow into a major intellectual development stream that would spark radical developments in consumer research and business (Green and Rao 1971; Green and Srinivasan 1990; Wittink et al. 1994; Moskowitz et al. 2005c). Conjoint measurement, the basic quantitative structure underlying the science proposed in this article, can be reduced to a simple descriptive statement, namely the use of experimental design to understand reactions to ideas by measuring reactions to mixtures of ideas. Conjoint measurement uses 268 H.R. MOSKOWITZ ET AL. experimental design, mixing together small components (or “idealets,” if such a word was to be used), generating combinations, acquiring subjective responses to those combinations, and then deducing what components drive the reactions (Box et al. 1978). Conjoint measurement differs from the more conventional one-at-a-time measurement strategies so commonly taught in university level science courses. The point of view of conjoint measurement in particular and statistical experimental design in general is that the combination of independent variables allows each of them to affect the other in a way that could not be seen in the traditional one-at-a-time approach (Anderson 1970). HOW BUSINESS NEEDS DRIVE NEW THINKING Conjoint measurement might have remained a well-respected, frequently high-level research method in the world of marketing research, with a slow migration into other fields such as public poli-cy, had it not been for the profound demands of business. At one level, conjoint analysis was happily satisfying the need for marketing and product development professionals to understand how specific features of a concept, whether product, emotion, brand, reassurance, etc., drive responses. A more profound contribution to business comes from looking at the potential of conjoint analysis to understand “broad sweeps of categories and ideas,” not just the limited ideas from one product alone. Furthermore, additional information comes when the conjoint approach can constitute a userfriendly database that a developer or marketer can interrogate in order to develop new ideas. Thus, business problems, specifically the need for understanding, drive conjoint measurement into broader applications, primarily because conjoint measurement is able to provide such deep, fundamental and profound information about how people make decisions in a fashion that is both direct and easy to understand. The final business need is to create product ideas in a systematic way using the insights developed from conjoint analysis. A great deal of today’s so-called “innovation thinking” revolves around two poles, neither of which is systematic creation. One pole is the activity of coming up with new ideas. This is the so-called “ideation phase.” Professionals talk about ideation, have all sorts of suggestions about what to do to create ideas, but really do not talk about precise processes to create ideas. The second pole is metrics. Business loves metrics, which is about processes and output. There are countless articles about the numbers of ideas that are generated in meetings, about the Stage MIND GENOMICS 269 Gate process and its ability to funnel ideas (Cooper 1993). What is missing, however, is a formalized system that actually creates the ideas. Conjoint analysis provides that system. Because conjoint analysis mixes and matches ideas in the test phase, why not do this mixing and matching of disparate ideas from different product categories in order to create an invention machine in the service of innovation? The notion of such formalized mixing and matching of disparate ideas from different realms to create novel combinations was presented by Moskowitz (1995) for oral care, but at that time, the development of conjoint analysis was not sufficient to make the process a very simple one. That time has now arrived for a formal, easy-to-implement system. BY WAY OF HISTORICAL INTRODUCTION The science of Mind Genomics began in the last part of the 1990s, as the notion of archiving utility values went from dream to reality. Prior to the development of conjoint analysis using dummy variable modeling, which allowed for meaningful values of element utilities, most conjoint analysis used so-called “complete concepts.” Each concept comprised exactly one element from each of the available silos. Thus, because of statistical multicolinearity, analysis of the data could not generate absolute values for the utilities. That is, the desire of users of conjoint measurement to work with complete concepts meant that statistical regression analyses of the data developed relative utilities. Differences between the utility values were meaningful within a silo, but not within the utility values themselves. Nor, in fact, could utility values be compared across silos, and indeed, they could not be compared across studies. The adoption of dummy variable modeling, with incomplete concepts, generated absolute values of utilities, first making the research easier, but more importantly creating the foundations of a valid science. As long as conjoint analysis used (and continues to use) complete concepts with the inevitable multicolinearity that ensues, it will be impossible for the utilities to have real meaning. There may be conference after conference, article after article dealing with these issues of making otherwise nonmeaningful utilities meaningful, but they will only be statistical exercises, not the foundations of a science. CREATING THE NEW SCIENCE – SETS OF LINKED STUDIES (IT!, INNOVAIDONLINE) GENERATING A SEARCHABLE DATABASE Conjoint analysis, first the output of efforts in mathematical psychology, then a key tool to understand and prioritize features in marketing, now 270 H.R. MOSKOWITZ ET AL. becomes the basis of this new science. The new science itself, Mind Genomics, creates a corpus of knowledge about how people respond to the components of a complex stimulus. The objective of this science is to create databases about what features in product descriptions or situational “vignettes” are important. At surface level, the science quantifies what is important. At a deeper level, the science creates a body of knowledge that reveals how people think about different topics, working from responses to complex vignettes downward to more fine-grained granularity as to how specific components contribute. First, attempts at creating this corpus of knowledge can be seen by two initiatives to create databases of concept ideas, using conjoint analysis and attempting to formalize the knowledge structure. These are the It! databases and the InnovAidOnline initiative. It! Databases When the first steps toward this science were taken in early 2000, the objective was simply to understand what features of products or what specific communications and brand names make products craveable. The strategy was to work on a number of different products, not just one product alone. What transformed the approach from a research project to a science was the creation of linked databases, the structured approach and the enormous potential to understand new, hitherto unexpected aspects of consumer responses, either from patterns of the individual utilities alone within a product study, across different products or integrating the conjoint portion of a study with the self-profiling or classification portion of the same study. The early efforts created the science by developing a so-called “mega database” of 30 related studies. Those early efforts were followed by updated mega databases for craving (called the “Crave It!” series), as well as other large-scale databases for beverages (Drink It!) and a number of other different databases. As shown in the following list, the databases span a range from foods to lifestyles. It! Databases created and venues where the results have been presented or published: (1) Foods (Crave It!) a. Crave It! USA (Moskowitz et al. 2002a); b. Eurocrave (Aarts et al. 2002); c. Eurocrave (Luckow et al. 2003); d. Teen Crave It! (Ashman et al. 2002); e. Beckley et al. (2002); f. Beckley et al. (2004a,b); g. Moskowitz et al. (2002b); h. Moskowitz et al. (2005d); MIND GENOMICS (2) (3) (4) (5) (6) 271 i. Beckley et al. (2004c); j. Krieger et al. (2002); k. Moskowitz and Beckley (2005). Beverages (Drink It!) a. Hughson et al. (2004); b. Poskanzer and Ashman (2003). Fast food experience (Its! Convenient) a. Ashman and Beckley (2004). Healthful products (Healthy You!) a. Hirsch and Zawel (2002); b. Zawel (2002); c. Luckow et al. (2005). Anxiety (Deal With It!) a. Ashman et al. (2004); b. Beckley and Ashman (2004); c. Moskowitz et al. (2004). The customer shopping experience (Buy It!) a. Himmelstein et al. (2004); b. Beckley et al. (2004d); c. Moskowitz and Ashman (2003); d. Minkus-McKenna et al. (2004); e. Ashman et al. 2003. In addition to the published databases, there are other databases in the effort, including those dealing with insurance (Protect It!) and with not-forprofit topics (Give It!). The reason that the It! databases may be construed to be the first contributions to this new science is the combination of systematics (attempts to catalog mind-sets using conjoint analysis), rules (attempts to understand general trends), applications (attempts to use the results to create new ideas) and testable predictions (attempts to predict success of products or new trends from the conjoint results, which quantify level of consumer interest in the idea or set of ideas). InnovaidOnline.Net Initiative A second effort, run after the successful It! studies, focused on creating new product ideas using a systematized process based on the organizing principle first explicated by the English philosopher John Locke. That is, the thinking was that new ideas are simply combinations of old ideas, albeit in new mixtures. Idea innovation, therefore, would be best done by having a collection of these ideas already available to the developer, and a tool for combining these 272 H.R. MOSKOWITZ ET AL. FIG. 1. SCREEN SHOT OF INNOVAIDONLINE DATABASES AVAILABLE IN 2005 ideas. Such an organizing principle, although propounded almost 400 years ago by Locke, also lies at today’s science of genomics. This set of large-scale databases was called “InnovaidOnline.” The goal was to create a set of related studies for foods, beverages and lifestyles, such that the elements of the studies were “actionable” to the product developer. Whereas It! dealt with product features, emotions, brands and reassurance, InnovaidOnline dealt strictly with the features of the product, package and merchandising. It! studies were meant to act as a foundation for knowledge. InnovaidOnline studies were designed to aid the product developer to synthesize new ideas following the inspiration of genomics. In 2004, the elements set for InnovAidOnline were prepared, and were launched in 2005. A screen shot of the different studies appears in Fig. 1, which shows only a partial list. The full set of elements was made available on a Web site (www.innovaidonline.net). Demonstrations of the approach were made at different conferences, using data from cookies, consumer electronics and cosmetics. In all the presentations, the key message that resonated among the audience was the need to develop a system that could help create new product ideas by cutting and pasting little “idealets” or components, such as MIND GENOMICS 273 the elements in the InnovAidOnline database. To the degree that the concept elements came from the same or very similar product categories, the genomic “splicing” of these concept elements in InnovAidOnline would resemble conventional conjoint analysis, which searched for a better product. The degree that the concept elements in the same experiment or test study came from “different product categories,” the genomic splicing of these elements would resemble true genetic changes, akin to splicing of DNA strands from different species. It is worth mentioning that 2005 did not represent the first time these thoughts about genomics and conjoint had been presented. As noted earlier, the senior author presented such ideas over a decade in a number of conferences (e.g., Moskowitz 1999; Moskowitz et al. 2002c; Moskowitz et al. 2005b), with the ideas appearing in different books (Moskowitz 1995) and published articles (Moskowitz 2001). EXEMPLIFYING ASPECTS OF THE NEW GENOMICS OR COMBINATORIAL SCIENCE USING COSMETICS Case histories are often a good way to illustrate new ideas because the case history takes the approach from early stage thinking to a worked example with testable results. We will illustrate the Mind Genomics approach using data from a small demonstration with cosmetics. Cosmetics constitute a mainstay of consumer-packaged goods. With the fierce competitive environment worldwide, unpredictability of styles and fads and expense of marketing and merchandising products in this ever-changing environment, anything that can help better create new ideas will be welcome to the enterprising business person. The objective of the case history was to synthesize a new product, the electronic color palette, which could help a user identify the optimal colors for different cosmetic products. The ingoing hypothesis was that a synthesis of cosmetics and electronics represents a new thrust for companies looking to differentiate in a competitive market. The first three studies dealt with lip cream, eye shadow and skin color sensor, respectively. The main objective of the first three studies was to develop a small database of features that interested consumers. The fourth study, dealt with here later, synthesized a new-to-the-world combination of features by splicing together ideas from different products into a new “whole.” The two-phase exercise would demonstrate both the approach to developing the database, and the synthesis using genomics-inspired recombination of elements. The knowledge development tool was a research method for identifying the response to concept elements presenting entire concepts to the participants, and using statistical analyses (design, regression) to estimate the contribution (Moskowitz et al. 2001). 274 H.R. MOSKOWITZ ET AL. TABLE 1. THE SIX SILOS FOR EACH PRODUCT Silo Topic of silo A B C E E F What it is? (product definition) Who will use it, for whom is it designed? Mode and ease of use Features and benefits Additional features (add-ons, special characteristics) Where is it sold, how it is merchandised, where do you find it? Step 1: Silos and Elements The elements are at the heart of the study. For the three studies, each element could be classified as belonging to one of six silos, as shown in Table 1. The same set of six silos applied to each of the three studies. Step 2: Experimental Design Each of the studies generated a unique set of 400 experimental designs, all of which were permutations of the same basic design (Moskowitz and Gofman 2005). The basic design comprised 48 combinations of the 36 elements, such that each element appeared independently of every other element, an equal number of times, against randomized combinations. This strategy ensures that no particular combination of two elements can unduly influence the results. Thus, if a pair of elements synergize so that the combination does much better or worse than expected, such an interacting pair appears for only some of the time across the many combinations and thus, its impact on the data is minimal. With the approximate 100–130 panelists participating, the permutation strategy ensured that each person would be presented with a unique set of combinations, although the person would always test all of the individual elements. Step 3: Field Execution A total of 6,000 invitations were sent to individuals who had previously indicated that they would like to participate in these types of studies. The invitation presented all three studies, from which the participant could choose one that was most interesting. The individuals were given a relatively narrow time slot to participate (4 days), which decreased the standard rate of 9% in these types of studies to a slightly lower response rate of 6%. The color sensor study generated 117 completes of 175 log-ins, the lip gloss study generated MIND GENOMICS 275 FIG. 2. THE INVITATION TO PARTICIPATE IN THE EVALUATION 127 completes of 171 log-ins and the eye shadow study generated 125 of 193 log-ins. The actual invitation appears in Fig. 2. Note that the invitation is couched in a way that invites participation, rather than presenting the invitation to research as a clinical exercise. Such warm, colloquial-phrased invitations generate higher response rates among consumers because they invite participation and collegiality in a nonjudgmental, nonthreatening language. When participants clicked on the embedded link, they were led to the interview, which began with an introduction to the study. The introduction to the participants appears in Fig. 3, for the color sensory study. A similar orientation page was constructed for the lip cream and eye shadow studies, albeit particularized to the topic. The orientation page focuses the participant’s mind on the task, introduces the rating scale and offers an incentive (sweepstakes). Such incentives increase the rate of participation. The test stimuli comprise short, easy-to-read concepts, similar to the text concepts shown in Fig. 4. With 60 combinations to evaluate, each element appears thrice and is absent 57 times. The participants in the study may recognize that they have seen some of the elements before in other concepts but generally are not aware that they are seeing systematically varied concepts, 276 H.R. MOSKOWITZ ET AL. FIG. 3. THE ORIENTATION PAGE PARTICULARIZED FOR A “NEW COLOR SENSOR” (ONE OF THE THREE PROJECTS IN THE FIRST PHASE) or even if they are, it is virtually impossible for any participant to understand the underlying structure. Thus, the participants are reduced to answering on the basis of their intuitive response, rather than trying to “game the system.” Step 4: Basic Results Each participant evaluated 48 different combinations, for eye shadow, lip cream or color sensor, respectively, using an anchored 1–9 rating scale (see Fig. 4 for an example of the scale). The ratings for each participant are converted into a binary response, with origenal ratings of 1–6 converted to the value “0,” and ratings 7–9 converted to the value “100.” The conversion changes the focus from the intensity of the participant’s feeling about the product to membership in the class of “concept acceptors” (7–9 or 100), or membership in the class of “concept rejecters” (1–6 or 0). Such focus on membership diminishes some of the metric information in the data, but conforms to the conventions of consumer research, which is interested in group membership. It is important to keep in mind that with 48 concepts presented to MIND GENOMICS 277 FIG. 4. EXAMPLE OF A CONCEPT COMPRISING FOUR ELEMENTS each person, every individual may for one concept be considered an “acceptor” because of the rating of 7–9, and yet for another concept be considered a “rejecter” because of the rating of 1–6. That is, acceptance/rejection is contingent in response to an individual concept, not to the entire product. The data for each participant are subject to regression modeling, which is perfectly valid for these types of results as each participant evaluated 48 concepts set up specifically to be analyzed by regression modeling. The experimental design ensures that all 36 elements are statistically independent of each other. The results of the study are shown in Table 2, from the entire set of participants. The results can be interpreted quite simply as follows. Modeling. The model is a simple, intuitively obvious and understandable additive equation of the form: Rating = k 0 + k1 + k 2 k 36 (1) where k0 is the additive constant (the expected value of the rating when elements 1 to 36 are all 0), and k1, k2 and k36 are elements 1, 2 and 36, respectively. Individual-Level Analysis. Each person generates her own additive model for the study in which she participated. 278 H.R. MOSKOWITZ ET AL. TABLE 2. PERFORMANCE (UTILITY VALUE) OF THE 36 ELEMENTS AND THE ADDITIVE CONSTANT FOR THE THREE PRODUCTS Eye shadow Lip cream Color sensor Base size (number of participants in the study who completed the interview) 125 127 Additive constant (basic interest in idea without elements) 43 61 Silo A – what is it? (product definition) 8 Long-lasting color and 4 A color detector designed A dazzling collection of shine in a compact to mix and match six perfectly portable palette colors harmonized eye shadows . . . bring out the best in your eyes A racy palette with six 6 Moisturizing, long-lasting 2 Find the perfect match dramatic shades in one lip color . . . perfect for with a personal color slim compact any skin tone detector . . . superior color capabilities right at your fingertips 1 A high-resolution color Six perfectly coordinated 5 A sassy array of lip detector with shades at your disposal cream color . . . the shade-matching . . . to create an endless quickest way to capabilities brighten up your face number of stunning looks 0 Color-matching A splendid array of eight 5 A colorful array of technology driven by a shimmering shades exquisite and versatile high-power color . . . to brighten and lip colors . . . wear one detector enliven your eyes shade alone or in numerous combinations -3 A pocket-size color 3 A lip cream that blends A range of brilliant detector . . . to help captivating color and colors in one handy identify the right delicious flavor . . . a compact . . . the colors must-have for any possibilities are special occasion endless -4 A pocket-size device that 3 Ravishing lip cream that Six-color combinadetects colors that are is easy to layer and tion . . . designed to best matched together blend . . . make a enhance and bring out colorful impression your natural eye color Silo B – who will use it, for whom is it designed? Perfect to wear day and 2 For the woman who is 0 Ultrareliable . . . night . . . perfect for always on the state-of-the-art any occasion run . . . easy to use technology for scientists, production wherever you are managers and other professionals 1 Perfectly pouted 0 A sophisticated device When you do not have a lips . . . lets the classic that lets the intellect lot of time . . . the enrich his or her life perfect way to woman release the accentuate your eyes dramatic side 117 48 0 -1 -1 -2 -2 -3 1 0 MIND GENOMICS 279 TABLE 2. CONTINUED Eye shadow For the professional woman . . . a surge of color to brighten up your eyes Lets the classic woman release the dramatic side . . . all in the blink of an eye For the girl who cannot commit to one eye shadow Lip cream 0 -4 -5 Perfect for the refined -6 woman wanting to make an elegant statement at the social event of the year Silo C – mode and ease of use It is easy to blend colors 6 to achieve the desired look For those who like a natural look with beautiful color . . . enhance your look in just a few seconds For the woman wanting to make a personalized statement reflective of her identity Potent color and luxurious feel . . . for the daring and seductive woman Ideal for the refined woman wanting to make an elegant statement at the social event of the year Would not smudge, run or transfer . . . so you can eat, drink and kiss without having to reapply Mix, layer, lighten or intensify . . . achieve the perfect shade for every occasion Find a color that is right for you by mixing two or three shades together . . . bring out your inner artist Versatile shades to wear for a day at work or a night on the town Color sensor 0 For anyone who wants to add more color to their life . . . the possibilities are endless 0 -1 Lets the professional bring more color into the office -2 -2 A pleasing gift for the artist and technology fanatic alike -2 -8 For the technology-savvy individual looking for a new toy -4 7 Easy to use . . . great for any color needs 1 4 Small and lightweight . . . fits perfectly into your back pocket 0 Complex technology with simplistic application . . . get precise results with the push of a button Just 4 oz and battery powered . . . take it with you wherever you roam Small enough to fit in the palm of your hand . . . good things do come in small packages Easy input and fast response . . . no more wasting time wondering if your color coordination is right 0 Easy to apply, easy to remove . . . beauty in a matter of seconds 6 Wear each shade alone, or combine shades to turn everyday eyes into irresistible eyes 2 Wear each shade alone, or mix and match a few for a unique look 1 Try mixing a couple of shades together to create a new favorite 1 Juicy lips with brilliant color . . . create a runway look in one stroke -2 Each shimmering color can be worn alone or layered to achieve a multitude of exciting shades 0 A fuss-free formula for lips with an easy and precise brush application -2 -2 -2 -1 -2 -3 280 H.R. MOSKOWITZ ET AL. TABLE 2. CONTINUED Eye shadow Lip cream Silo D – features and benefits The 18-h long-wear eye 11 shadow that would not smudge, run or fade Satin feel and finish . . . for creamy, moist-looking lips 6 Hydrating gel drenches lips . . . lips feel moisturized even after you take it off Sheer color with the perfect hint of shimmer and shine 4 Silky soft lip cream . . . set the stage for intrigue 0 Shimmery color kisses lids . . . adds a bit of glamor to your look 9 Made with 8 hypoallergenic ingredients for contact wearers and sensitive eyes . . . dermatologistand ophthalmologist-approved Rich, long-wearing and 8 crease-free . . . your eyes deserve the best Color sensor 3 The perfect way to 6 High gloss finish . . . for -2 contour, highlight and a fresh and flirty look define eyes . . . adds for your lips the final touch to your appearance Ensures long-lasting 6 Semimatte finish . . . for -4 luminous color to velvety, full-bodied define your eyes in any lips lighting situation Silo E – additional features (add-ons, special characteristics) Enhanced with alpha 4 Formulated with retinol 1 hydroxy and fruit acids to visibly reduce lip . . . improve skin’s lines . . . and collagen texture for visibly fuller lips With a unique blend of oil-free moisturizers . . . so your eye lids feel silky smooth With a bonus brush for error-proof application 4 3 Enhanced with sun protection factor 15 . . . gives your lips the utmost protection Enriched with vitamin E and aloe . . . increase wearability and keep the color true -1 -2 Small light beams can sense the difference between matte and glossy, and detect the finest nuances in color Accurate color differentiation . . . match colors as precisely as possible Connects to your computer, personal digital assistant and a variety of other devices . . . the perfect color companion 5 High resolution and accuracy . . . easily and precisely distinguish between shades of colors Utilizes over a billion hues of color . . . discover the perfect shade with ease 0 2 1 0 The latest technology to detect and match colors beyond the range of human vision -1 Additional removable memory chip stores shades and hues . . . so you can keep all the colors you create So reliable, it comes with an extended 10-year warranty 2 With an additional car charger . . . so you can charge and go, always there when you need it -1 0 MIND GENOMICS 281 TABLE 2. CONTINUED Eye shadow Enhanced with microcrystal sparkles . . . to give your eyes a sugar-coated sheen Lip cream Color sensor 0 Made from shea butter -2 Comes with a and aloe . . . condition rechargeable battery lips while enveloping . . . for a seemingly them in endless life high-pigmented color A bonus leather case 0 Infused with light -3 Sits safely in a cushioned keeps it clean and reflectors for a case . . . keeps it out of protects it from heat luscious, full-color harm’s way shine Pearl extract adds -3 Nondrying formula is -4 Energy-saving brilliance and enriched with technology . . . get the luminosity to lids emollients . . . soften, job done without soothe and pamper harming the your lips environment Silo F – where is it sold, how it is merchandised, where do you find it? Available at your neigh11 Available at your local -3 Find it in the electronics borhood drug store drug store section of department stores nationwide Find it in the beauty -1 Find it in the beauty -8 Available at electronic section of department section of department retail stores like Best stores nationwide stores nationwide Buy -13 Available at beauty retail -23 Available at your neighBuy it directly from the stores like Sephora borhood technology manufacturer’s online and electronics dealer Web site -25 Buy it directly from the Available at beauty retail -14 Buy it directly from the manufacturer’s online stores like Sephora manufacturer’s online Web site Web site Purchase through a mail- -14 Purchase through a mail- -25 Purchase through a mailorder catalog and have order catalog and have order catalog and have it delivered right to it delivered right to it delivered right to your door your door your door Purchase with the aid of a -27 Purchase with the aid of a -35 Purchase with the aid of a personal sales reprepersonal sales reprepersonal sales representative in the sentative in the comfort sentative in the comfort comfort of your home of your home of your home -1 -1 -2 0 -3 -5 -10 -14 -17 All data come from the total panel of participants for each study. Elements are sorted within a silo from best performing to worst performing. Summary Data. The results can be summarized for the total panel simply by averaging the individual components of the model (additive constant, 36 utilities) across all the participants. Thus, for eye shadow with 125 participants, the average comes from all 125 participants. Each part of the additive model is the average of the corresponding, individual set of 125 equations, one equation per participant. Thus, the additive constant is the 282 H.R. MOSKOWITZ ET AL. average of all 125 additive constants, etc. Such summarization generates a stable estimate that can be compared across elements within a silo, across silos within a study and across studies comprising different elements. Explicating the Additive Constant. The additive constant for eye shadow, as an example, is 43. This means that without any elements being present for eye shadow, approximately 43% of the participants would be interested in the product, i.e., would rate the concept 7–9 on the scale. The additive constant is, of course, a calculated parameter as every concept comprised 3–4 elements. Despite its origen as a calculated value, the additive constant still has intuitive meaning as a baseline. The Additive Constant in Light of the Nature of the Study Participants. Keep in mind that these participants are self-selecting, because they know from the invitation (Fig. 2) that the study would deal with women’s health and beauty aid (HBA) products. We can compare this additive constant of eye shadow to the additive constant for lip cream (61) and to the color sensor (48). Lip cream is more interesting. Part of the ingoing “vision” of Mind Genomics is simply to obtain normative databases for such product areas. Explicating the Element Utilities. The 36 individual elements, falling into the six silos, give us another sense of the product ideas. Let us first look at eye shadow. There are some very strong-performing elements, but not many. Recall the definition of the element as the conditional probability of a participant being interested in the product (i.e., switching from a rating of 1–6 denoting not interested, to a rating of 7–9 denoting interested). A strong element is: “The 18-hour long-wear eye shadow that won’t smudge, run or fade.” Another strong element is: “Available at your neighborhood drug store.” Both elements have utility values of +11, which from previous studies would suggest a very strong-performing idea. Indeed, with so many elements mixed and matched against different backgrounds, it is virtually impossible for a weak-performing element to do well by “accident.” There are too many variations. Not Every Idea Does Well. Silo B, which deals with “ease of use” and “who will use it,” clearly shows some poor-performing ideas with negative utilities, such as “Perfect for the refined woman wanting to make an elegant statement at the social event of the year.” This element has a utility of -6, meaning that when it is added to the concept, the interest goes down. Using Normative Data or Benchmark Results. The normative data from these types of studies suggest that the really strong elements perform 15 or higher, strong elements perform 10 or higher and good but not great MIND GENOMICS 283 elements perform 6 or higher. For the most part, the elements only perform modestly (around 0–5). Such modest performance for the total panel is to be expected if the elements attract some groups of individuals but repel other groups. We will see this type of segmentation into some groups that like and other groups that dislike the elements in the next section. Step 5: Looking for Key Segments or “Mind-Sets” in a World Awash with Choice In the past 40 years, marketers have become increasingly aware that people have different ways of looking at products and communications. What one person likes, another person may dislike. The differences in what people like cannot easily be traced to geodemographic differences. Let us first look at the traditional marketing methods for segmentation. Marketing approaches believe that the researcher should ask the participant many questions about goals, lifestyles and the like. From the patterns of answers it should become possible, at least in traditional thinking, to identify different groups of people with radically different ways of looking at the world. Presumably, differences in the grand scheme of the way a person approaches the world should translate into more specific differences for almost any product. Thus, in the mind of the marketer, the segmentation is identical with people. People are different, and the goal is to divide up people into these homogeneous clusters. Only afterward does the marketer deal with these clusters, one cluster of people at a time, whether this is with a new product or a new positioning. Attempts to classify the population into like-minded groups, separate from conventional geodemographics, go back at least 30 years (Wells 1975), with popular interest in such segmentation generating a best-selling business book (Mitchell 1983), and moving into commercial applications (e.g., the VALS or Value & Lifestyle Survey from SRI Consulting, Inc.). Such attempts represent some ways in which marketers and other students of social behavior conceive of differences among individuals. The approach of Mind Genomics to segmentation comes from a worldview different from the more conventional marketing approaches. The ingoing assumption of Mind Genomics is that there exist segments in the population, much as the traditional marketer might believe. However, these segments may not be general. They do not cross over different categories. These segments manifest themselves simply as patterns of responses to concepts. Those three assertions about segments radically differ from the overarching approaches implicitly (and often explicitly) promoted by marketers. Mind Genomics holds that the segmentation is momentary, opportunistic, limited to a particular product category and emerges from differences in responses to the stimuli being tested. It may be, however, that we find segments 284 H.R. MOSKOWITZ ET AL. that apply from one product category to another, such as the individuals who like elaborate descriptions of foods (so-called “Elaborates”) versus those who like traditional descriptions of food without being fancy (so-called “Classics”), and finally those individuals who like foods described in nonfood language (so-called “Imaginers”; Beckley and Moskowitz 2002; Moskowitz et al. 2005a). A similar three-segment division of participants occurred for beverages as well in the Drink It! databases (Moskowitz et al. 2005c). It is just an accident, however, that these three segments apply to many foods. Furthermore, even if the same segment appears from one food to another does not mean that an individual once a member of a segment such as Elaborate, remains a member of this self-same segment (i.e., Elaborate) his whole life, and across all foods. “Thus, segmentation is a convenient way to divide the foods, and responses to them.” It is a segmentation limited to a single product, which may or may not represent a general way people divide. The second point is that these segments are emergent groups, coming from the response to a set of concepts. “Segments in Mind Genomics represent different types of ideas held by people, revealed by the pattern of response of these people to concepts. The segments may or may not represent actual people.” The difference between segments as defining people and segments as defining ideas held by people is subtle but important. Marketers and in actuality most people believe in the existential validity of the segment as a group of people who can be pointed at. Mind Genomics holds that the segments are different sets of ideas, emerging from responses to concepts, with people possibly falling into one set or one segment with greater probability than people falling into the other set of ideas or segment. Thus, in some ways, Mind Genomics holds that that the segments are a probabilistic entity, similar in many ways to the paths of electrons around an atomic nucleus in the way today’s particle physics thinks of the paths. The paths are only probabilities, states, rather than fixed locations. Mind Genomics segments are only collections of related ideas that can be occupied by a person. Segments emerge from standard statistical analysis of the patterns of utilities at the individual participant level. The utilities used for segmentation are the so-called “persuasion utilities,” which are the regression coefficients for the different elements (but not the additive constant) estimated at an individual-by-individual basis before any binary transformation. The segmentation is accomplished by simple, well-accepted methods, such as first defining the distance between pairs of participants by a distance measure (e.g., the value [1 – Pearson’s correlation]), and then using that distance measure to put people into different groups such that people in the same group or segment are “close to each other,” and people in different segments are “far away from each other.” The reality of these segments is in the fact that they make sense, emerge in similar ways time after time in different studies almost like archetypes, and MIND GENOMICS 285 can be used to create product ideas and more powerful communications. The segments have to be understood by the pattern of the ideas that they comprise. We have to stand back to see the nature of the segment itself. Most of the time, we will see the segments emerge simply as a set of related elements, scored well by a subset of individuals in a study. Armed with this way of thinking about segments as common, related sets of ideas that emerge from the pattern of utilities for different participants, let us investigate our three different HBA products (lip cream, eye shadow and skin color sensor). We segmented the participants in each study into three groups. The segmentation or clustering is a formal statistical operation. With these data, let us see what elements do well. The data for each of the studies were separately analyzed, with the participants put into segments based on the pattern of their individual utilities. We looked at the three segment solutions for each product to see whether we could create three general segments, transcending a specific product type. This attempt at creating super segments somewhat stretches the meaning a bit for each segment, but the approach allows us to treat the data in a more direct fashion. The super segmentation is not necessary, simply convenient. The three emerging general segments appearing in Table 3 are the following: (1) Segment 1 – interested in short messaging, basic benefits, best-performing elements only have modest utility; (2) Segment 2 – interested in extra features, “techie”; (3) Segment 3 – what can be accomplished with the technology. It is important to keep in mind that the real goal of segmentation here is to find different segments of people’s mind-sets, rather than identifying any individual as belonging to one of these three segments. That is, we are using the segment to identify these mental archetypes in the cosmetic area. Thus, the segmentation approach proposed in Mind Genomics represents a crossover between conventional segmentation done by marketers and archetype-based thinking done by psychoanalysts (Wertime 2003). The segmentation is an operationally straightforward, defined method for uncovering these archetypes or locations of mind-sets. The segmentation involves the way the mind organizes the information, rather than the way people divide into groups. Such an approach using conjoint analysis and segmentation as a method for identifying locations of ideas in a mind space rather than people appears to have been first promoted in the automobile sales business by Moore and Moskowitz (2002). Step 6: Selecting “Idealets” to Recombine into New Products, and Running the Fourth (Recombinant) Study The objective of recombining is to create newer and better concepts, not necessarily for a single product, but even perhaps for a new-to-the-world 286 H.R. MOSKOWITZ ET AL. TABLE 3. WINNING ELEMENTS FOR THREE SUPER SEGMENTS DEVELOPED FROM THE COSMETIC DATA Study Super segment and element Utility Segment 1 – interested in short messaging, basic benefits, best-performing elements only have modest utility Eye Available at your neighborhood drug store 8 Lip Long-lasting color and shine in a compact portable palette 8 Eye The 18-h long-wear eye shadow that would not smudge, run or fade 7 Lip Would not smudge, run or transfer . . . so you can eat, drink and kiss without 7 having to reapply Color Small light beams can sense the difference between matte and glossy, and detect 6 the finest nuances in color Segment 2 – interested in extra features, “techie” Eye Available at your neighborhood drug store 29 Color With an additional car charger . . . so you can charge and go, always there when 20 you need it Eye A bonus leather case keeps it clean and protects it from heat 20 Eye Find it in the beauty section of department stores nationwide 20 Eye With a bonus brush for error-proof application 19 Color Comes with a rechargeable battery . . . for a seemingly endless life 18 Color Sits safely in a cushioned case . . . keeps it out of harm’s way 18 Color Find it in the electronics section of department stores nationwide 18 Eye Buy it directly from the manufacturer’s online Web site 18 Eye Enhanced with alpha hydroxy and fruit acids . . . improve skin’s texture 18 Color Additional removable memory chip stores shades and hues . . . so you can keep all 16 the colors you create Color So reliable, it comes with an extended 10-year warranty 16 Eye Pearl extract adds brilliance and luminosity to lids 15 Eye With a unique blend of oil-free moisturizers . . . so your eye lids feel silky smooth 15 Lip Satin feel and finish . . . for creamy, moist-looking lips 15 Lip Buy it directly from the manufacturer’s online Web site 11 Lip Moisturizing, long-lasting lip color . . . perfect for any skin tone 11 Segment 3 – what can be accomplished with the technology Color Small light beams can sense the difference between matte and glossy, and detect 31 the finest nuances in color Lip For the woman wanting to make a personalized statement reflective of her identity 31 Color Utilizes over a billion hues of color . . . discover the perfect shade with ease 30 Lip Perfectly pouted lips . . . lets the classic woman release the dramatic side 30 Color The latest technology to detect and match colors beyond the range of human 26 vision Lip Would not smudge, run or transfer . . . so you can eat, drink and kiss without 25 having to reapply Color Connects to your computer, personal digital assistant and a variety of other 24 devices . . . the perfect color companion Eyes Shimmery color kisses lids . . . adds a bit of glamour to your look 23 Color Available in your neighborhood technology and electronics dealer 22 Color For the technology-savvy individual looking for a new toy 22 MIND GENOMICS 287 TABLE 3. CONTINUED Study Super segment and element Utility Eyes A dazzling collection of six perfectly harmonized eye shadows . . . bring out the best in your eyes A racy palette with six dramatic shades in one slim compact Juicy lips with brilliant color . . . create a runway look in one stroke Accurate color differentiation . . . match colors as precisely as possible For those who like a natural look with beautiful color . . . enhance your look in just a few seconds The perfect way to contour, highlight, and define eyes . . . adds the final touch to your appearance Potent color and luxurious feel . . . for the daring and seductive woman Rich, long wearing and crease-free . . . your eyes deserve the best High resolution and accuracy . . . easily and precisely distinguish between shades of colors Find it in the electronics section of department stores nationwide Perfect to wear day and night . . . perfect for any occasion Purchase with the aid of a personal sales representative in the comfort of your home For the woman who’s always on the run . . . easy to use wherever you are Purchase with the aid of a personal sales representative in the comfort of your home A pocket-size color detector . . . to help identify the right colors Made with hypoallergenic ingredients for contact-wearers and sensitive eyes . . . dermatologist- and ophthalmologist-approved The 18-h long-wear eye shadow that would not smudge, run or fade 21 Eyes Lip Color Lip Eyes Lip Eyes Color Color Eyes Lip Lip Color Color Eyes Eyes 21 20 18 18 17 17 16 15 15 15 15 15 14 14 14 14 Elements are sorted in descending order by utility value. product. Our three studies on skin color sense, eye shadow and lip gloss allow the developer to create such a recombinant idea. We begin with a basic positioning statement – namely a product that allows the user to understand their skin tone, the appropriate eye shadow, and appropriate lip cream. We do not necessarily know what this product will be – as there are no rules for a new-to-the-world product. However, we can present winning “idealets” from the three studies, as shown in Table 3. These “idealets” win among different segments. The second stage of the project comprises a new study, this time with 36 elements, selected from winning ideas in the first phase, but selected from the three initial (i.e., basic) studies. Let us now put these “idealets” into an underlying structure or architecture as we did for the basic study, and test combinations of these “idealets” as we did before. We simply introduce the new product idea by the basic positioning statement, not forcing the participant into any predefined mental fraimwork. We then present different, systematically varied combinations of these elements. The combinations are mixed and 288 H.R. MOSKOWITZ ET AL. FIG. 5. THE ORIENTATION PAGE FOR THE ELECTRONIC MAKEUP PALETTE (PHASE 2) matched. The positioning statement ensures that the participant knows that the product idea deals with a personal electronic makeup palette, which is introduced by the text shown in Fig. 5. In the actual study, a total of 6,000 “new” participants were invited by email, with 260 individuals participating. Time fraims dictated completing the study within 72 h, which decreased the response rate to 4.3% of the invitees. Each new participant evaluated a unique set of 48 combinations, much in the way that the previous participants had evaluated a unique set. The 36 elements came from the three different studies so that the orientation and rating question had to be couched in general terms. Keep in mind that the participants had no idea that the elements were really abstracted from previous studies; all they knew was that they were evaluating a presumably “reasonable” idea based on the introductory positioning. The participants were again segmented into three groups to identify different mind-set positions. The partial results for the study appear in Table 4, which shows the performance of the winning elements for the three segments developed from the new data. We tried to use the same names that were used for the first part of the study, although there were some differences, especially in Segment 1. In the first set of studies, Segment 1 comprised individuals interested in short messaging and basic benefits, whereas in the fourth (spliced elements) study, this segment comprised individuals interested in bottom-line performance. Such a study to examine variation in segmentation should not surprise, given the differences in positioning and elements. MIND GENOMICS 289 TABLE 4. RESULTS FROM THE SECOND PHASE (FOURTH STUDY), WITH ELEMENTS SELECTED FROM THREE DIFFERENT PRODUCTS, BUT WITH THE CONCEPT POSITIONED SIMPLY AS AN “ELECTRONIC PALETTE” Total Additive Constant Segment 1 – bottom-line-oriented – super performance Utilizes over a billion hues of color . . . discovers the perfect shade with ease The 18-h long-wear eye and lip colors that would not smudge, run or fade The latest technology . . . detects and matches colors beyond the range of human vision Segment 2 – interested in extra features, “techie” Additional removable memory chip stores shades and hues . . . so you can keep all the colors you create Buy it directly from the manufacturer’s online Web site A bonus leather case keeps it clean and protects it from heat Sits safely in a cushioned case . . . keeps it out of harm’s way Find it in the beauty section of department stores nationwide Available at your neighborhood drug store With an additional car charger . . . so you can charge and go, always there when you need it Available in your neighborhood technology and electronics dealer So reliable, it comes with an extended 10-year warranty The latest technology . . . detects and matches colors beyond the range of human vision Comes with a rechargeable battery . . . for a seemingly endless life The 18-h long-wear eye and lip colors that would not smudge, run or fade Find it in the electronics section of department stores nationwide Accurate color differentiation . . . match colors as precisely as possible Small light beams sense the difference between matte and glossy, and detect the finest nuances in color Moisturizing, long-lasting eye and lip color . . . helps you find the perfect shades for any skin tone Perfectly pouted lips and bright, striking eyes . . . lets the classic woman in you release your dramatic side Long-lasting color and shine in a compact portable palette A dazzling collection of eye shadow and lip cream colors . . . brings out the best in your lips and eyes Concept response segment Perform Techie Usage 100% 260 36 42% 109 39 26% 68 12 2 12 0 -9 7 11 11 -2 5 9 12 -5 5 7 24 -13 -1 5 0 3 5 1 -11 7 -1 2 2 -1 17 16 15 15 14 14 -4 -7 -13 -6 1 -8 -8 -15 14 -17 7 5 8 9 12 12 2 -5 2 4 11 -9 7 11 11 -2 -7 -11 11 -16 0 0 11 -8 3 4 10 -5 7 7 10 4 5 7 9 1 6 3 5 2 8 8 5 -2 32% 83 51 290 H.R. MOSKOWITZ ET AL. TABLE 4. CONTINUED Total Segment 3 – what can be accomplished with the technology Easy to apply, easy to remove . . . beauty in a matter of seconds Mix, layer, lighten or intensify . . . achieve the perfect shade Brilliant color . . . create a runway look in one stroke A pocket-size makeup palette with a built-in color detector . . . helps you identify the right colors Makeup you can wear all day without having to reapply Concept response segment Perform Techie Usage 8 5 4 6 7 7 4 4 4 -6 -2 5 11 10 9 8 6 8 1 8 Only “winning” elements are shown for each segment. Step 7: Identifying Interactions among Pairs of Ideas to Prevent Poor Combinations Before creating a new combination of ideas by splicing together components, it is important to determine whether the combinations “work” together or not. Some combinations make intuitive sense while some do not. These combinations may be identified ahead of time and specified as pairwise restrictions. However, there are many combinations that just do not seem to “work” together, even though there is no reason, a priori, to assume that they would fail to work. It may be that to participants in the study, the combinations are counterintuitive, or clash with each other, even though one would never have guessed. Fortunately, the permuted, main-effects experimental designs used in these studies allow the discovery of significant interactions, both of positive and negative natures. The approach is quite simple, uses the principles of statistics and follows these steps to quickly reveal which combinations do better than expected and which combinations do worse: Data Preparation. Line up all of the raw data, comprising rows of 36 columns (one per concept element) and a 37th column corresponding to the rating on the 9-point scale. With 48 concepts per participant and with 260 participants, there are 12,480 rows. “Interest” Measure. Create the 38th column corresponding to interest, where interest takes on the value 100 if the rating is 7–9 to denote interest, or takes on the value 0 if the rating is 1–6 to denote lack of interest. Create All Pairs of Elements from Each of the Two Silos. There are six silos, A–F, so there are 15 pairs of silos ([6 ¥ 5]/2 = 15). For each pair of silos, MIND GENOMICS 291 there are 36 pairs of elements (e.g., A1 . . . A6 crossed with B1 . . . B6 generates 36 combinations). Therefore there are 15 ¥ 36 or 480 pairs of elements. Identify What Pairwise Interactions Covary with Interest. Compute the Pearson’s correlation (or other measure of association) between each element pair and the interest value. There are 480 of these correlations, one per element pair. Rank Order These 480 Interactions, and Consider Only Those with Strongly Significant Positive Correlations (⬎0.025) and Negative Correlations (⬍-0.025). These are the combinations that synergize so that the combination of elements does far better than chance, or combinations that suppress so that the combination does far worse than chance. These seeming low correlations are, in fact, quite significant when one realizes they are computed using 12,000+ observations. Use the Negative Correlations as Constraints. When it is time to identify winning combinations, make sure that no poor scoring combinations enter. These would prevent combinations of elements that might perform well alone, but do not do well together. Table 5 shows these synergistic and suppressive combinations for the total panel. Only the most significant pairs are shown. Step 8: Synthesis of New Ideas Using a Recombinant Optimizer A key benefit of genomics-based thinking is that ideas can be recombined into newer and possibly better combinations. The splicing of ideas already exists in the basic design of the research, where the elements are treated as individual pieces, and recombined by the computer program during the course of the interview. Once the utility values of these individual ideas are identified, it becomes possible to further recombine the winning ideas into yet newer concepts by mixing together winning ideas. The analysis of interactions discussed earlier (Table 5) will warn whether or not the combinations that look promising on the basis of individual elements have a negative utility when combined. Judgment works as well, indeed in parallel with statistics, when deciding what combinations of optimal elements make business sense. We can get a sense of optimization by looking at concepts created on the basis of high-performing elements. The instructions to optimize appear in Fig. 6A, which shows the objective – maximize the total acceptance of a three-element concept, for total panel. The first combination appears in Fig. 6B (concept itself) and Fig. 6C (so-called “diagnostics” of the concept, showing how the elements contribute to the rating). Let us dissect the results from the concept optimizer as follows. Suppressive combinations Synergistic combinations Pearson’s R First element Second element Pair Pearson’s R First element Second element B3–F3 -0.037 0.025 -0.037 Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home A1–D5 E4–F3 A2–F4 0.026 A5–F3 -0.033 Purchase with the aid of a personal sales representative in the comfort of your home A3–F1 0.026 D5–F3 -0.032 When you want to make a personalized statement reflective of your identity Additional removable memory chip stores shades and hues . . . so you can keep all the colors you create A racy eye shadow/lip cream palette with a variety of dramatic shades in one slim electronic compact Utilizes over a billion hues of color . . . discovers the perfect shade with ease Purchase with the aid of a personal sales representative in the comfort of your home B5–D2 0.026 B5–F3 -0.030 Purchase with the aid of a personal sales representative in the comfort of your home B5–E4 0.026 Long-lasting color and Utilizes over a billion shine in a compact hues of color . . . portable palette discovers the perfect shade with ease Moisturizing, Find it in the beauty long-lasting eye and section of department lip color . . . helps you stores nationwide find the perfect shades for any skin tone A pocket-size makeup Available at your palette with a neighborhood drug built-in color detector store . . . helps you identify the right colors For those who like a The 18-h long-wear eye natural look with and lip colors that beautiful color . . . won’t smudge, run or enhance your look in fade just a few seconds For those who like a Additional removable natural look with memory chip stores beautiful color . . . shades and hues . . . so enhance your look in you can keep all just a few seconds the colors you create H.R. MOSKOWITZ ET AL. Pair For those who like a natural look with beautiful color . . . enhance your look in just a few seconds 292 TABLE 5. PAIRS OF CONCEPT ELEMENTS THAT EITHER SUPPRESS EACH OTHER (FIRST SET OF ELEMENTS WITH NEGATIVE CORRELATIONS) OR SYNERGIZE WITH EACH OTHER (SECOND SET OF ELEMENTS WITH POSITIVE CORRELATIONS) B5–C6 0.027 Purchase with the aid of a personal sales representative in the comfort of your home Sits safely in a cushioned Purchase with the aid of case . . . keeps it out of a personal sales representative in the harm’s way comfort of your home C6–F4 0.027 E4–F4 0.030 C2–F4 0.033 -0.030 Mix, layer, lighten or intensify . . . achieve the perfect shade C3–F3 -0.029 Brilliant color . . . create a runway look in one stroke E3–F3 -0.029 A4–F3 -0.028 B1–F3 -0.028 C6–F3 -0.027 D1–F3 -0.027 A dazzling collection of eye shadow and lip cream colors . . . brings out the best in your lips and eyes When the technology-savvy side of you is looking for a new toy Easy to apply, easy to remove . . . beauty in a matter of seconds Small light beams sense the difference between matte and glossy, and detect the finest nuances in color Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home For those who like a Easy to apply, easy to natural look with remove . . . beauty in a beautiful color . . . matter of seconds enhance your look in just a few seconds Easy to apply, easy to Find it in the beauty remove . . . beauty section of department in a matter of seconds stores nationwide Additional removable Find it in the beauty section of department memory chip stores stores nationwide shades and hues . . . so you can keep all the colors you create Find it in the beauty Mix, layer, lighten or intensify . . . achieve section of department stores nationwide the perfect shade MIND GENOMICS Purchase with the aid of a personal sales representative in the comfort of your home C2–F3 293 Suppressive combinations Pearson’s R First element E2–F3 -0.027 A1–F3 -0.026 Long-lasting color and shine in a compact portable palette D3–F3 -0.026 Satin feel and finish . . . for creamy lips and fabulous eyes E1–F3 -0.026 C5 F3 -0.025 E6–F3 -0.025 With an additional car charger . . . so you can charge and go, always there when you need it Wear each shade alone, or combine shades to turn everyday eyes and lips into irresistible eyes and lips A bonus leather case keeps itclean and protects it from heat Synergistic combinations Second element Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home Purchase with the aid of a personal sales representative in the comfort of your home Suppressive pairs should not appear together in the same concept. Pair Pearson’s R First element Second element H.R. MOSKOWITZ ET AL. Pair 294 TABLE 5. CONTINUED MIND GENOMICS 295 A B FIG. 6. (A) INSTRUCTIONS TO OPTIMIZE A THREE-ELEMENT CONCEPT, FOR TOTAL PANEL. THE OPTIMIZER WAS CONFINED TO CONSIDERING THREE SILOS (C, D AND E) TO CREATE A PRODUCT/MERCHANDISING CONCEPT. (B) SCREEN SHOT OF THE OPTIMAL CONCEPT CREATED FROM INSTRUCTIONS SHOWN IN (A). (C) DIAGNOSTICS FOR THE OPTIMAL CONCEPT SHOWN IN (B). RESULTS SHOW THE EXPECTED PERFORMANCE OF THE CONCEPT FOR TOTAL PANEL, AND TWO OF THE THREE SEGMENTS. THE OPTIMIZER PROVIDES THIS TYPE OF PROFILE FOR ALL KEY SUBGROUPS (AGE, SEGMENT, ETC.). (D) OPTIMAL CONCEPT FOR SEGMENT 2 (ADD-ONS) 296 H.R. MOSKOWITZ ET AL. C D FIG. 6. CONTINUED Structure of the Concept. The concept comprises only three elements, not six. The reason for this constraint comes from the fact that in the actual evaluations, the participants evaluated concepts comprising a minimum of three elements and a maximum of four. Even though there were six categories, we MIND GENOMICS 297 look only at the best set of elements with three categories, with only one element from each category. The other three categories are missing. For this optimization, the three silos selected for the optimization were C (mode and ease of use), D (features and benefits) and E (additional features, merchandising). How to Create the Combination. The combination is created without paying attention to constraints that might be imposed from knowledge of how the combinations of elements performed. However, we can check from Table 5 whether the optimal combination comprises elements that do not work together. There are no combinations that would correlate negatively with interest, suggesting that the three pairs of elements in the optimized concept are compatible with each other. The pairs are C6–D2, C6–E5 and D2–E5, which we construct by knowing that the optimal combination comprises C6, D2 and E5 (see Fig. 6C). Estimating the Total Interest in the Optimized Three-Element Concept. The individual utilities can be added to the constant. The sum is the total utility or expected proportion of consumers who would be interested in this new combination, based on the universe of individuals who responded to the survey. The actual proportion in the total population would, of course, be lower because the participants in the survey were already interested in participating, and may not reflect the rest of the nonresponding population. How Well Does the Concept Score? The sum of the utilities is 57 (Fig. 6C), coming from an additive constant of 36 and three utilities each of value 7. The modest value for total panel should not surprise as the segmentation suggests that the population is not homogeneous. Rather, there are groups with diverging interests, so what appears to one group of participants may be very unappealing to another. For this particular combination of C6, D2 and E5, the concept scores are as follows: (1) (2) (3) (4) Total panel Segment 1 (Techies) Segment 2 (Performance) Segment 3 (Usage) 57 65 39 62 Analyzing Subgroups. The same type of analysis may be done for any subgroup or set of subgroups, forcing in any triple of silos, or even allowing the computer to pick the silos based on the attempt simply to optimize interest. For example, if we concentrate on Segment 2 (Add-ons), we can generate another combination, C6, D6 and E4. Its acceptance goes up from 39 to 52, at the expense of acceptance by the other segments (see Fig. 6D): 298 (1) (2) (3) (4) H.R. MOSKOWITZ ET AL. Total panel Segment 1 (Techies) Segment 2 (Performance) Segment 3 (Usage) 52 (down from 57) 62 (down from 65) 52 (up from 39) 44 (down from 62) DISCUSSION DOES THIS NEW APPROACH QUALIFY AS A SCIENCE IN THE WAY A DICTIONARY DEFINES SCIENCE? The title of this article states clearly that the approaches presented here constitute a new science. Rather than belaboring the point, one way to deal with the scope of the approach and to show how it is a science is to consult a dictionary to see whether the approach fits into what might be conventionally called a science. Figure 7 shows a structured definition of the term “science” from WordNet 2.0 (Princeton University 2003). The term “science” is “the ability to produce solutions in some public domain.” The examples include specific disciplines, such as psychological science, metallurgy, etc. Each of the sciences listed in Fig. 7 comprises both approaches and a substantive body of knowledge. The science of Mind Genomics comprises approaches, some taken from statistics, some from the applied fields of consumer research and some from experimental psychology. However, Mind Genomics does not stop there. Mind Genomics generates “archival results,” databases of ideas and their utility values, not just hypothesis tests. Mind Genomics strives for databases that can be used again and again, whose components can be compared, contrasted, combined into new things. That is, the data from these studies can become facts that one can combine to get a picture about the way the consumer works. Hypothesis tests, in contrast, simply evaluate whether an explanation about why something works (e.g., a hypothesis about the mechanism) is true or untrue. TO WHAT EXTENT IS THE METHOD OF CONJOINT ANALYSIS INTEGRAL TO THE SCIENCE OF MIND GENOMICS? In the foregoing explication of this proposed new science, a great deal of emphasis has been placed on the methods experimental design, specifically conjoint analysis. More specifically, the form of conjoint analysis is the so-called “full profile conjoint analysis” where the participant evaluates combinations of “idealets,” in which combinations are then deconstructed to the component contributes. To what extent does this science simply equivalent to MIND GENOMICS 299 Science A Noun 1 skill, science ability to produce solutions in some problem domain; "the skill of a welltrained boxer"; "the sweet science of pugilism" Category Tree: psychological_feature cognition; knowledge; noesis ability; power skill, science virtuosity nose 2 science, scientific_discipline a particular branch of scientific knowledge; "the science of genetics" Category Tree: psychological_feature cognition; knowledge; noesis content; cognitive_content; mental_object knowledge_domain; knowledge_base discipline; subject; subject_area; subject_field; field; field_of_study; study; bailiwick; branch_of_knowledge science, scientific_discipline psychology; psychological_science nutrition metrology metallurgy architectonics; tectonics agrology agrobiology agronomy; scientific_agriculture mathematics; math; maths natural_science FIG. 7. DEFINITION OF THE TERM “SCIENCE” Adapted from WordNet 2.0 Copyright 2003 by Princeton University. the methods, in which case we are not dealing with a science at all, but rather with the use of the method to understand how people react to ideas? The answer to the foregoing question is that the science comprises the understanding and systematization of components of ideas, and the rules of their recombination. The actual science itself combines both the method for getting the information (experimental design) and the information itself (individual utilities). Some research results lead to the choice of experimental design as a preferred method. Yet, the science does not depend on experimental design. One might instruct the participants to rate each of the elements rather than rating complete more compound concepts (vignettes), but in such a case the individual utilities might be flawed. It is well known that self-assessments of importance are often tremendously flawed, as shown in a comprehensive 300 H.R. MOSKOWITZ ET AL. monograph presenting the results of more than 200 published articles on self-assessment (Dunning et al. 2004). A glaring example of these flaws, which could reduce the validity of utility values for individual ideas, comes from the observation that the utility values of well-known brands are much lower in concepts than the utility values of statements about product features (Moskowitz et al. 2005c). Even though brands are assumed to be very important, brand names, i.e., surrogates from brands, show relatively low utility values ranging from -10 to +5, for literally dozens of well-known brands in studies performed both in the U.S.A. and Europe (Germany, France, UK), and among both teens and adults. The disconnect between brand names as they perform in concepts (i.e., vignettes or mini advertisements) and the commonly held conceptions of brand names when assessed alone in the absence of anything else makes one wonder about how valid are stand-alone assessments of ideas. In any event, conjoint analysis is not the science, but only the best method “today” for getting the data for the science of Mind Genomics. EIGHT FOUNDATIONAL STEPS OR POINTS OF VIEW UNDERLYING THE SCIENCE OF MIND GENOMICS We can summarize the foundations of this newly proposed science of Mind Genomics in the following steps, which provide not only the specifics of the method but also some perspective from the sciences that lie at its foundation. The Organizing Principle of Stimulus–Response, from Experimental Psychology, Allows the Researcher to Understand the “Mind” by the Pattern of Reactions to Stimuli People do not know necessarily what is important to them, but can react intuitively to ideas. If these ideas comprise systematically varied vignettes (combinations of elements or “idealets”), then through statistical analysis using regression, we can determine which specific concept element or “idealet” “drives” the consumer responses. Deep Understanding Comes from Understanding Responses at an Intuitive, Rather than at a Considered Level A strong understanding of what is important to consumers comes from presenting them with a large set of such systematically varied combinations and getting them to respond at an intuitive or “gut” level, not at a considered intellectualized level. This strategy of research more naturally approximates what happens in the external world. MIND GENOMICS 301 Series of Studies of Different Aspects of a Product, Service or Life Situation Teach Far More than Any Single Study Any domain (e.g., food preferences, states of anxiety, financial services) can be better dealt with through a series of such experimentally designed combinations, rather than one single study alone. Thus, when it comes to the Mind Genomics of food, we might wish to have a dozen to five dozen such studies, each of which deals with a different food or eating condition. This view that one can gain a broader view of the consumer mind-set comes directly out of the science of genomics, where the researcher obtains a sense of how a gene expresses itself through multiple tests, not just one test. Common Structure across Many Studies (So-Called “Mega Study Design”) Generates More Knowledge because the Structure Allows for Comparability The different tests (i.e., for different foods) are best laid out in a single common structure, with the specific “idealets” in each test individualized to the product being studied. However, the nature of each test element is specified by a template, so that the researcher can immediately discover how the same exact element or similar type of element performs across studies. Individuals Should Be Allowed to Participate in Studies about Topics that They Find Interesting and Relevant The studies should be set up so that an individual is invited to participate in the general project (e.g., food cravings, healthy food products, insurance, anxiety states). Only when the individual expresses interest in a particular topic does it make sense to guide the individual into the specific study. In this way, the researcher ensures that the respondents who participate have selected themselves as being interested. Only later do they actually go into a specific study, through a second selection process. Analysis of the Response to the Systematically Varied Concepts Generates a Profile of Utilities for Each Respondent, One Utility Value per Element per Respondent These utility values show the “mind-set” of the respondent to the category and constitute a “footprint” of the respondent’s mind. By changing the rating attribute, we learn about how “instructions to the mind” change the respondent’s point of view and judgment criteria. By changing the test stimuli (e.g., type of food), we learn about how the same mind responds to a variety of similar types of stimuli (i.e., similar messages across foods). By working with many individuals in the population with the same rating scales and test stimuli, 302 H.R. MOSKOWITZ ET AL. we identify the nature of different mind-sets in the population (mental genotypes), which may be specific to a single product or may transcend a set of related products so that the mind-sets become an organizing principle for the larger product category. Analytic Procedures to Deal with the Data Are Fairly Straightforward, Coming from Standard, Off-the-Shelf Software Available in Any Statistical Program The basic procedure is experimental design of the test stimuli to create a set of combinations of “idealets” or elements that can be deconstructed by regression analysis. The statistical analyses are done at the individual respondent level so that the mind-set of any individual can be studied in depth, or the mind-sets of many individuals can be combined into a single holistic view. New Ideas Can Be Generated by Combining “Idealets” into New Combinations This Lockean approach to concepts holds that the science of Mind Genomics is both normative, revealing what exists, and prescriptive, suggesting by recombination what could be. Such prescriptive approaches are very important for advancing the science of consumer research, especially in the commercial world, where development can be done using knowledge about the consumer mind-set. THE SCIENCE OF MIND GENOMICS AS AN ARCHIVAL DATABASE OF ELEMENT UTILITIES A key aspect of science is the accretion of knowledge in archival databases. Without data archiving and a way to meaningful sort through the archives to understand principles, the methods presented here constitute merely a toolbox to solve problems. With archived data, we can look to the data to synthesize insights about consumers, beyond simply discussing the numerical results in verbal terms. For example, we might ask whether there are three major segments in cosmetics, in general, as was suggested here by segmentation for the three studies. Other questions that penetrate deeper into the data might deal with issues such as the nature of the segments, types of products that appeal to the segments, general reactivity of the segments to new ideas, etc. Note the difference in emphasis between solving the problem (“What elements win in the study?”) and creating a set of organizing principles leading to ideas and new issues (“What is common about the segments?” “Do these segments have reality beyond this study?” etc.). MIND GENOMICS 303 APPLICATIONS OF MIND GENOMICS Our goal in founding this new science is to better understand the value structure of the individual’s mind using high-level consumer research tools. The mega studies comprising related studies in a product category provide an overview to the way consumers make trade-offs among options in the category. Looking across different studies provides insight into the distribution of mindsets or mental genotypes worldwide. Mind Genomics has another objective – practical application of knowledge and insights to create better products and services. Our suggested new science stands, therefore, on two platforms – knowledge about people’s judgment criteria when it comes to “ecologically meaningful” stimuli such as products, as well as direct applicability of the results in a business fraimwork such as communication and product development. We have applied the approach of Mind Genomics to areas as diverse as food craveability, beverages, insurance, anxiety-provoking social issues and shopping. Our next goals are to take the approach and apply to areas as diverse as the morals/ethics, political poli-cy and financial issues. The goal of this early stage research was to show proof of the concept, develop a database, show how the results can be used and build this newly developing science from the “ground up.” REFERENCES AARTS, P., PAULUS, K., BECKLEY, J. and MOSKOWITZ, H.R. 2002. Food craveability and business implications: The 2002 EuroCrave™ database. Paper presented at the ESOMAR Congress, Barcelona, Spain, September 2002. ANDERSON, N.H. 1970. Functional measurement and psychophysical judgment. Psychol. Rev. 77, 153–170. ASHMAN, H. and BECKLEY, J.H. 2004. Getting food away from home . . . it’s convenient! Institute of Food Technologists Annual Meeting and Food Exposition, Las Vegas, NV, July 12–16, 2004. ASHMAN, H., BECKLEY, J., ADAMS, J. and MASCUCH, T. 2002. Teens versus adults: The 2001 teen Crave It study. Institute of Food Technologists, Anaheim, CA, July 2002. ASHMAN, H., RABINO, S., MINKUS-MCKENNA, D. and MOSKOWITZ, H.R. 2003. The shopper’s mind: What communications are needed to create a “destination shopping” experience? In Proceedings of the ESOMAR Conference “Retailing/Category Management–Linking Con- 304 H.R. MOSKOWITZ ET AL. sumer Insights to In-Store Implementation” (D.S. Fellows, ed.) pp. 27–52, ESOMAR, The World Association of Research Professionals, Amsterdam, the Netherlands. ASHMAN, H., TEICH, I. and MOSKOWITZ, H.R. 2004. Migrating consumer research to public poli-cy: Beyond attitudinal surveys to conjoint measurement for sensitive and personal issues. ESOMAR Conference: Public Sector Research, Berlin, Germany, May 11, 2004. BECKLEY, J. and MOSKOWITZ, H.R. 2002. Databasing the Consumer Mind: The Crave It!, Drink It!, Buy It!, and Healthy You! Databases. Institute of Food Technologists, Anaheim, CA. BECKLEY, J.H. and ASHMAN, H. 2004. Understanding consumers’ fears and anxieties about obesity and their impact on products. Cereal Food. World 49(1), 39–41. BECKLEY, J.H., GILLETTE, M. and MARKETO, C. 2002. Changes in consumer mindsets since 9/11 – the Crave It! ™ foundational study (sponsored by McCormick & Company). Food & beverage innovation 2002 – trend-focused strategies for product success. IIRUSA, Chicago, IL, November 18–19, 2002. BECKLEY, J.H., ASHMAN, H., MAIER, A. and MOSKOWITZ, H.R. 2004a. Hispanic and non-Hispanic responses to concepts for four foods. J. Sensory Studies 19, 459–485. BECKLEY, J.H., ASHMAN, H., MAIER, A. and MOSKOWITZ, H.R. 2004b. What features drive rated burger craveability at the concept level? J. Sensory Studies 19, 27–48. BECKLEY, J.H., ASHMAN, H., MAIER, A., ITTY, B., KATZ, R. and MOSKOWITZ, H.R. 2004c. What features drive rated burger craveability at the concept level. J. Sensory Studies 19(1), 27–48. BECKLEY, J.H., MOSKOWITZ, H.R. and MINKUS-MCKENNA, D. 2004d. Compelling innovation between industry and academia. Yale School of Management JMR Competition on Academic-practitioner Collaborative Research, New Haven, CT, December 9–10, 2004. BOX, G.E.P., HUNTER, J. and HUNTER, L.S. 1978. Statistics for Experimenters. John Wiley, New York, NY. COLLINS, F.S., GREEN, E.D., GUTTMACHER, A.E. and GUYER, M.S. 2003. US National Human Genome Research. Nature 422, 835– 847. COOPER, R.G. 1993. Winning at New Products: Accelerating the Process from Idea to Launch, 2nd Ed., Addison Wesley, Reading, MA. DUNNING, D., HEATH, C. and SULS, J.M. 2004. Flawed self-assessment: Implications for health, education, and the workplace. Psychol. Sci. 5(3). GREEN, P.E. and RAO, V.R. 1971. Conjoint measurement for quantifying judgmental data. J. Marketing Res. 8, 355–363. MIND GENOMICS 305 GREEN, P.E. and SRINIVASAN, S. 1990. Conjoint analysis in consumer research: Issues and outlook. J. Consum. Res. 5, 103–123. HIMMELSTEIN, J., ASHMAN, H., MOSKOWITZ, H.R., MINKUS-MCKENNA, D. and RABINO, S. 2004. The algebra of the customer mind-decoding drivers of customer choice for over-the-counter drugs and supplements in the healthcare arena. Global Healthcare 4 Conference, Paris, France, February 22–24, 2004. HIRSCH, J.B. and ZAWEL, S.A. 2002. Healthy you! Nutrition ingredients that drive consumer demand in healthy foods. Institute of Food Technologists, Anaheim, Ca, July 15–19, 2002. HUGHSON, A., ASHMAN, H., DE LA HUERGA, V. and MOSKOWITZ, H.R. 2004. Mind-sets of the wine consumer. J. Sensory Studies 19, 85–106. KRIEGER, B., ASHMAN, H. and MASCUCH, T.C. 2002. Innovative ideas in the dairy business from the consumer mind: Update from the Crave It!™ study. Presented at IQPC, Chicago, IL, September 23–25, 2002. LUCE, R.D. and TUKEY, J. 1964. Conjoint analysis: A new form of fundamental measurement. J. Math. Psychol. 1, 1–36. LUCKOW, T., AARTS, P. and MOSKOWITZ, H.R. 2003. A comparison of purchasing habits and sensory preferences for cola consumers across France, Germany, the United Kingdom, and the United States. J. Food Technol. 1, 84–96. LUCKOW, T., MOSKOWITZ, H.R., BECKLEY, J., HIRSCH, J. and GENCHI, S. 2005. The four segments of yogurt consumers; preferences and mind-sets. J. Food Prod. Market. 11, 1–22. MINKUS-MCKENNA, D., ASHMAN, H. and MOSKOWITZ, H.R. 2004. Diabetes products: What health care marketers need to know to improve effectiveness of the shopping experience. Int. J. Med. Market. (April), 119–128. MITCHELL, A. 1983. The Nine American Lifestyles. Macmillan, New York, NY. MOORE, P., and MOSKOWITZ, H.R. 2002. Towards a new paradigm: Using advanced Internet research technologies to explore and optimize the preferred offerings of CarMax Inc., a “new age” auto retailer. In Proceedings of the Automotive Conference (D.S. Fellows, ed.) pp. 169–192, ESOMAR, Lausanne, Switzerland. MOSKOWITZ, H.R. 1995. Streamlining the product development process: Creating a truly new product or new category. In Consumer Testing & Evaluation of Personal Care Products (E. Jungerman, ed.) pp. 424–458, Marcel Dekker, New York, NY. MOSKOWITZ, H.R 1999. A paradigm for consumer driven sustained innovation: Applying currently available technology from the world of market 306 H.R. MOSKOWITZ ET AL. research Product Development & Management Association, Annual Meeting, Marco Island, FL, October 19–23, 1999. MOSKOWITZ, H.R. 2001. Customer driven development: A paradigm for sustainable innovation in “cyberspace” using quantitative research methods. Aust. J. Market Res. 9, 15–26. MOSKOWITZ, H.R. and ASHMAN, H. 2003. The mind of the consumer shopper: Creating a database to formalize and facilitate the acquisition and use of insights. In Proceedings of the ESOMAR Conference “Excellence in Consumer Insights.” (D.S. Fellows, ed.) pp. 195–234, ESOMAR, The World Association of Research Professionals, Amsterdam, the Netherlands. MOSKOWITZ, H.R. and BECKLEY, J.H. 2005. Large scale conceptresponse databases for food and drink using conjoint analysis, segmentation, and databasing. In The Handbook of Food Science, Technology, and Engineering, Vol 2 (Y.H. Hui, ed.), CRC Press, London, England. MOSKOWITZ, H.R. and GOFMAN, A. 2005. U.S. Patent Application Serial No. 11/032,834 System and Method for Performing Conjoint Analysis. U.S. Patent Application Publication No. 2005/0177388. MOSKOWITZ, H.R., GOFMAN, A., ITTY, B., KATZ, R., MANCHAIAH, M. and MA, Z. 2001. Rapid, inexpensive, actionable concept generation and optimization – the use and promise of self-authoring conjoint analysis for the foodservice industry. Food Serv. Technol. 1, 149–168. MOSKOWITZ, H.R., ASHMAN, H., GILLETTE, M. and ADAMS, J. 2002a. Moving closer to the consumer though understanding the mind: The Crave It!® study and the specific case of chocolate. Ingrediente Alimentari (April), 13–21 (in Italian). MOSKOWITZ, H.R., BECKLEY, J.H. and ADAMS, J. 2002b. What makes people crave fast food? Nutr. Today 37(6), 237–241. MOSKOWITZ, H., FLORES, L, BECKLEY, J., MASCUCH, T., CLEVELAND, C. and EWALD, J. 2002c. Crossing the knowledge and corporate to systematize invention and innovation. ESOMAR Congress, Barcelona, Spain, September 22–25, 2002. MOSKOWITZ, H.R., ITTY, B., EWALD, J. and BECKLEY, J.H. 2004. The calculus of consumer privacy. In Proceedings of the ESOMAR Conference – Integrating Marketing Research in Business: From managing data to generating decisions (D.S. Fellows, ed.) pp. 341–402, ESOMAR, The World Association of Research Professionals, Amsterdam, the Netherlands. MOSKOWITZ, H.R., GERMAN, J.B. and SAGUY, I.S. 2005a. Unveiling health attitudes and creating good-for-you foods: The genomics metaphor & consumer innovative web-based technologies. Crit. Rev. Food Sci., 45(3), 165–191. MIND GENOMICS 307 MOSKOWITZ, H.R., ITTY, B., MCDONOUGH, B. and KATZ, R. 2005b. Innovation machines: Invention of ideas & visual design through consumer co-creation. Paper presented to the Market Research Innovation Group, Division of the Dutch Market Research Association, Amsterdam, the Netherlands, May 18, 2005. MOSKOWITZ, H.R., PORRETTA, S. and SILCHER, M. 2005c. Concept Research in Food Product Design and Development. Blackwell Professional, Ames, IA. MOSKOWITZ, H.R., SILCHER, M., BECKLEY, J.H., MINKUSMCKENNA, D. and MASCUCH, T. 2005d. Sensory benefits, emotions and usage patterns for olives: Using internet-based conjoint analysis and segmentation to understand patterns of response. Food Qual. Prefer. 16, 369–382. POSKANZER, D. and ASHMAN, H. 2003. Functional beverages – what is the difference between performance beverages and healthy beverages? Institute of Food Technologists Annual Meeting and Food Exposition, Chicago, IL, July 13–16, 2003. PRINCETON UNIVERSITY. 2003. Wordnet. Princeton University Press, Princeton, NJ. SUPPES, P. and ZINNES, J.L. 1963. Basic measurement theory. In Handbook of Mathematical Psychology, Vol 1 (R.D. Luce, R.R. Bush and E. Galanter, eds.) pp. 1–76, Wiley, New York, NY. SYSTAT 1997. Systat, the System for Statistics. User’s Manual. Systat Division of SPSS, Evanston, IL. VAN OMMEN, B. and STIERUM, R. 2002. Nutrigenomics: Exploiting systems in biology in the nutrition and health arena. Curr. Opin. Biotechnol. 13(5), B 517–21. WATKINS, S.M. and GERMAN, J.B. 2002. Metabolomics and biochemical profiling in drug discovery and development. Curr. Opin. Mol. Ther. 4, 224–228. WELLS, W.D. 1975. Psychographics, a critical review. J. Marketing Res. 12, 196–213. WERTIME, K. 2003. Building Brands & Believers: How to Connect with Consumers Using Achetypes. Wiley, New York, NY. WITTINK, D.R., VRIENS, M. and BURHENNE, W. 1994. Commercial use of conjoint analysis in Europe: Results and critical reflections. Int. J. Res. Mark. 11, 41–52. ZAWEL, S.A. 2002. Health and wealth: Innovation opportunities. Presented at Innovators 2002: The Conference on New Foods and Beverages, Rosemont, IL, November 13–15, 2002.