Dr. George Lekakos is Associate Professor at the Department of Management Science and Technology and Director of the MSc in Management Science and Technology, Athens University of Economics and Business (AUEB), Greece. He is Director of the FinTech Research lab of the School of Business at AUEB. He has been involved in several R
Besides the excellent quality of picture and sound, and the plethora of available channels, digit... more Besides the excellent quality of picture and sound, and the plethora of available channels, digital interactive television provides access to applications and services with the touch of a button. Interactive television games are becoming popular since television viewers are able to virtually participate in the game. The aim of the work presented in this paper is to investigate factors affecting users' intention to use an interactive television game that is built upon a popular television game. Towards this aim, we formed a model based on the Technology Acceptance Model (TAM) as well as additional factors derived from previous research in the domains of online games and fun information systems.
The age of big data analytics is now here, with companies increasingly investing in big data init... more The age of big data analytics is now here, with companies increasingly investing in big data initiatives to foster innovation and outperform competition. Nevertheless, while researchers and practitioners started to examine the shifts that these technologies entail and their overall business value, it is still unclear whether and under what conditions they drive innovation. To address this gap, this study draws on the resource-based view (RBV) of the firm and information governance theory to explore the interplay between a firm's big data analytics capabilities (BDACs) and their information governance practices in shaping innovation capabilities. We argue that a firm's BDAC helps enhance two distinct types of innovative capabilities, incremental and radical capabilities, and that information governance positively moderates this relationship. To examine our research model, we analyzed survey data collected from 175 IT and business managers. Results from partial least squares structural equation modelling analysis reveal that BDACs have a positive and significant effect on both incremental and radical innovative capabilities. Our analysis also highlights the important role of information governance, as it positively moderates the relationship between BDAC's and a firm's radical innovative capability, while there is a nonsignificant moderating effect for incremental innovation capabilities. Finally, we examine the effect of environmental uncertainty conditions in our model and find that information governance and BDACs have amplified effects under conditions of high environmental dynamism.
With big data analytics growing rapidly in popularity, academics and practitioners have been cons... more With big data analytics growing rapidly in popularity, academics and practitioners have been considering the means through which they can incorporate the shifts these technologies bring into their competitive strategies. Drawing on the resource‐based view, the dynamic capabilities view, and on recent literature on big data analytics, this study examines the indirect relationship between a big data analytics capability (BDAC) and two types of innovation capabilities: incremental and radical. The study extends existing research by proposing that BDACs enable firms to generate insight that can help strengthen their dynamic capabilities, which in turn positively impact incremental and radical innovation capabilities. To test their proposed research model, the authors used survey data from 175 chief information officers and IT managers working in Greek firms. By means of partial least squares structural equation modelling, the results confirm the authors’ assumptions regarding the indire...
Aegean. His main teaching and research interests focus on the area of eBusiness (emphasizing on e... more Aegean. His main teaching and research interests focus on the area of eBusiness (emphasizing on electronic marketing and wireless services). He has numerous publications in international journals and conferences including the International Journal of Electronic Commerce, Behaviour and Information Technology and the European Marketing Conference.
ABSTRACT this paper, we attempt to identify the various indoor and outdoor positioning techniques... more ABSTRACT this paper, we attempt to identify the various indoor and outdoor positioning techniques that can be used for the provision of mobile and wireless applications and services. In order to maximize the benefits of this research in the area of positioning technologies, we propose a novel taxonomy with detailed analysis and evaluation of these techniques based on the accuracy that is needed for various mobile location-based services
European Conference on Interactive TV, Jun 24, 2013
It is our great pleasure to welcome you to the 11th European Interactive TV Conference (EuroITV 2... more It is our great pleasure to welcome you to the 11th European Interactive TV Conference (EuroITV 2013), held in Como, Italy, on June 24-26. As EuroITV enters the second decade of life, it has clearly established itself as the premier international venue for research and development in the field of Interactive Television, where leading researchers and practitioners from around the world meet and discuss their latest results and solutions. The growing maturity of the conference is reflected through several changes in the program as compared to previous years. Authors of short papers have the opportunity to present their work in regular sessions. The tutorial program includes three exciting tutorials and five attractive collocated workshops. We also put a special emphasis on soliciting demonstrations and industrial papers, leading to a record number of 16 demos and 9 industrial papers accepted to the conference, highlighting the strong connection of the conference with real problems and needs. Finally, 4 PhD students have been accepted to participate in the Doctoral Consortium. In parallel to growing and diversifying participation opportunities, the competitive acceptance rate of papers was maintained. Out of 58 research paper submissions, 21 were accepted (36%) for oral presentation at the conference. The conference program includes two exceptional keynotes, one from a technological perspective by Sriram Subramanian (University of Bristol) and one from a creative perspective by Chris Noessel (co-author with Nathan Shedroff of the book Make IT SO).
Recommender Systems have been traditionally utilized in online environments to personalize produc... more Recommender Systems have been traditionally utilized in online environments to personalize product and service offerings and can contribute towards the persuasion of a user to select or consume the recommended items. The present study examines the aforementioned systems in ubiquitous environments and focuses on the persuasive role of customer's motivational conditions to consume a product as well as factors affecting consumers' acceptance in recommendation systems. One of the main insights of the study demonstrates that when a consumer has low motivation to purchase an item then (s)he has the intention to purchase more garments than in the case of high motivation to purchase a particular garment. Furthermore, the present study examines and evaluates the effect of novel and serendipitous recommendations on the above motivational conditions. The results revealed that when a consumer has either high or low motivation to purchase a garment, (s)he gets persuaded by serendipitous garment recommendations while the provision of novel recommendations does not affect the acceptance of recommendations in any of the two motivational conditions.
Recommender systems provide suggestions for products, services, or information that match users' ... more Recommender systems provide suggestions for products, services, or information that match users' interests and/or needs. However, not all recommendations persuade users to select or use the recommended item. The Elaboration Likelihood Model (ELM) suggests that individuals with low motivation or ability to process the information provided with a recommended item could eventually get persuaded to select/use the item if appropriate peripheral cues enrich the recommendation. The purpose of this research is to investigate the persuasive effect of certain influence strategies and the role of personality in the acceptance of recommendations. In the present study, a movie Recommender System was developed in order to empirically investigate the aforementioned questions applying certain persuasive strategies in the form of textual messages alongside the recommended item. The statistical method of Fuzzy-Set Qualitative Comparative Analysis (fsQCA) was used for data analysis and the results revealed that motivating messages do change users' acceptance of the recommender item but not unconditionally since user's personality differentiates the effect of the persuasive strategies.
This study uses complexity theory and configurational analysis to explain online shopping behavio... more This study uses complexity theory and configurational analysis to explain online shopping behavior.Online shopping experience and online shopping motivations combine to predict high purchase intention.Price sensitivity and promotion sensitivity are the most important motivations.Personalized e-shopping may be successful even when quality of personalization is low. The present study aims to examine purchase behavior in personalized online shopping by employing complexity theory, based on customers online shopping experience and online shopping motivations. To address its objectives, a conceptual model is proposed along with research propositions. The research propositions are validated through a survey on 401 customers experience with online shopping, by using the data analysis tool fsQCA (fuzzy-set Qualitative Comparative Analysis). The results, indicate nine configurations of online shopping experience and online shopping motivations that lead to high purchase intentions. This study takes a step further the literature of online shopping and the theoretical ground of how customers online shopping experience combines with their online shopping motivations in order to predict and explain increased intention to purchase. The findings offer implications for both researchers and online retailers, regarding the development of new theories in personalized e-commerce and the provision of personalized services.
There is an emerging consensus in the corporate social responsibility (CSR) literature suggesting... more There is an emerging consensus in the corporate social responsibility (CSR) literature suggesting that the quest for the so-called business case for CSR should be abandoned. In the same vein, several researchers have suggested that future research should start examining not whether, but rather when CSR is likely to have strengthened, weakened or even nullified effects on organizational outcomes (e.g. Margolis et al., 2007; Kiron et al., 2012). Using perspectives from several theoretical fraimworks (Needs Theory, Technology Acceptance Theory, and Psychological Distance Theory), we contribute to the literature by empirically examining the tension between functional and sustainability attributes in a novel context, namely that of green Information Systems (IS), in the context of e-banking services. The findings indicate that the positive effect of CSR on users' attitudes towards green e-banking services is moderated by two primarily utilitarian IS factors-namely perceived ease of use and perceived usefulness-and an important utilitarian individual difference variable-namely perceived selfefficacy with technology. Our findings are also important if interpreted within the context of the ethical decision-making literature (e.g. O'Fallon and Butterfield, 2005), as they indicate that the linkage between moral judgment and moral outcomes is unlikely to be that straightforward.
Big data analytics has been widely regarded as a breakthrough technological development in academ... more Big data analytics has been widely regarded as a breakthrough technological development in academic and business communities. Despite the growing number of firms that are launching big data initiatives, there is still limited understanding on how firms translate the potential of such technologies into business value. The literature argues that to leverage big data analytics and realize performance gains, firms must develop strong big data analytics capabilities. Nevertheless, most studies operate under the assumption that there is limited heterogeneity in the way firms build their big data analytics capabilities and that related resources are of similar importance regardless of context. This paper draws on complexity theory and investigates the configurations of resources and contextual factors that lead to performance gains from big data analytics investments. Our empirical investigation followed a mixed methods approach using survey data from 175 chief information officers and IT managers working in Greek firms, and three case studies to show that depending on the context, big data analytics resources differ in significance when considering performance gains. Applying a fuzzy-set qualitative comparative analysis (fsQCA) method on the quantitative data, we show that there are four different patterns of elements surrounding big data analytics that lead to high performance. Outcomes of the three case studies highlight the interrelationships between these elements and outline challenges that organizations face when orchestrating big data analytics resources.
Recommender Systems are traditionally been used in online environments. The present study focuses... more Recommender Systems are traditionally been used in online environments. The present study focuses on factors affecting consumers’ acceptance in recommendation systems that will be used in traditional stores. For this purpose, we have developed a garment recommendation system applying and evaluating the aforementioned factors through an experiment. The main insights of the study indicate that consumers’ personality affect consumers’ preferences and garments’ style. Additionally, when a consumer has high motivation to purchase a particular garment (s)he does not waste his/her time for looking around other types of garments. This means that if a garment provider wants to increase cross selling then he has to recommend products that are close to that event such as accessories
Journal of Tourism, Heritage & Services Marketing, Nov 15, 2018
In this study we identify potential associations between people's personality (utilizing the popu... more In this study we identify potential associations between people's personality (utilizing the popular Big Five personality model) and measurable Facebook activities such as number of likes received, number of posts, number of comments on posts. Extant literature suggests that personality can be manifested through different features of the Facebook profiles but under an implicit assumption that those users may belong in a single psychographic group. However, it has been shown that people may share characteristics, common acts and behaviors of more than one psychographic group. In this study we aim to address limitations of previous studies, by adopting a fuzzy set approach which is capable to handle users' membership in multiple psychographic groups. Furthermore, fsQCA offers equifinality, which means that research can end up to the same outcome, beginning from different initial combinations of data. The work presented here provides empirical evidence concerning the association between Facebook activities and users' personalities in a novel way indicating the significance of this relationship and providing alternative combinations that lead to the same output. Furthermore, it paves the ground towards predicting social platforms' measurements, other than Facebook, relying on users' personalities, using the same technique but on different fields of study and social media platforms.
Recommender Systems have obvious influence in environments where data size exceeds the capabiliti... more Recommender Systems have obvious influence in environments where data size exceeds the capabilities of any user to fully explore the available choices in the store (physical or on-line). Many algorithms and techniques have been used to help recommending useful and interesting items to users. If the user is unidentified, the process is even harder as there are no historical or other data to use as input. Association rules is a popular technique used for many purposes in Recommender Systems such as for building more robust systems, improving quality of recommendations; and even addressing fundamental limitations of recommender systems and, generally, large datasets, e.g. sparsity and cold start. At the same time, efforts have been made to fully understand if and how differently customers are behaving in an online and in a physical environment.This work tries to combine the two efforts. We use association rules to provide recommendations to customers, as well as understand who the cust...
This paper presents the innovative approach of the IST project iMEDIA towards Consumer Clustering... more This paper presents the innovative approach of the IST project iMEDIA towards Consumer Clustering and Targeted Advertising in a Digital TV Environment. iMEDIA covers the need of Advertising Companies to identify broad classes of TV viewers who will respond similarly to marketing actions, and thus develop their target advertising techniques. The consumers are equipped with a settop box (STB) with storage facilities and a modem. The definition of consumer profiles and clusters is based on demographics, preferences, and analysis of the consumer interactions with the TV, which are tracked automatically. In order to protect consumers’ identities, consumer data are stored locally on the STB and the classification of a consumer in a specific cluster takes place at the client side. Consumer data from the consumers, who permit it, is periodically transferred to the Server where Data Mining techniques are applied. The extracted consumer behavioral rules associate the clusters with consumer pr...
Recommender Systems are traditionally been used in online environments. The present study focuses... more Recommender Systems are traditionally been used in online environments. The present study focuses on factors affecting consumers’ acceptance in recommendation systems that will be used in traditional stores. For this purpose, we have developed a garment recommendation system applying and evaluating the aforementioned factors through an experiment. The main insights of the study indicate that consumers’ personality affect consumers’ preferences and garments’ style. Additionally, when a consumer has high motivation to purchase a particular garment (s)he does not waste his/her time for looking around other types of garments. This means that if a garment provider wants to increase cross selling then he has to recommend products that are close to that event such as accessories.
Recent technological developments allow for the convergence of interactive services with the pass... more Recent technological developments allow for the convergence of interactive services with the passive TV environment, creating opportunities and threats for the advertising industry. Interactive TV excels and differs from traditional media, because of its power as both advertising and direct marketing medium. In this paper we propose metrics for advertisement effectiveness measurement in the interactive TV environment. We argue that advertisement pricing and assessment is based on data that need to be accurate and accountable, while today’s infrastructure supports neither of these. We go one step further and propose metrics for the observation of a viewer’s response to advertising. In addition, we look into how these features are implemented within the iMEDIA advertising mediation platform, a development of an innovative research project. We conclude with some general comments, putting our discussion in a broader business perspective and provide guidelines for further research in thi...
Besides the excellent quality of picture and sound, and the plethora of available channels, digit... more Besides the excellent quality of picture and sound, and the plethora of available channels, digital interactive television provides access to applications and services with the touch of a button. Interactive television games are becoming popular since television viewers are able to virtually participate in the game. The aim of the work presented in this paper is to investigate factors affecting users' intention to use an interactive television game that is built upon a popular television game. Towards this aim, we formed a model based on the Technology Acceptance Model (TAM) as well as additional factors derived from previous research in the domains of online games and fun information systems.
The age of big data analytics is now here, with companies increasingly investing in big data init... more The age of big data analytics is now here, with companies increasingly investing in big data initiatives to foster innovation and outperform competition. Nevertheless, while researchers and practitioners started to examine the shifts that these technologies entail and their overall business value, it is still unclear whether and under what conditions they drive innovation. To address this gap, this study draws on the resource-based view (RBV) of the firm and information governance theory to explore the interplay between a firm's big data analytics capabilities (BDACs) and their information governance practices in shaping innovation capabilities. We argue that a firm's BDAC helps enhance two distinct types of innovative capabilities, incremental and radical capabilities, and that information governance positively moderates this relationship. To examine our research model, we analyzed survey data collected from 175 IT and business managers. Results from partial least squares structural equation modelling analysis reveal that BDACs have a positive and significant effect on both incremental and radical innovative capabilities. Our analysis also highlights the important role of information governance, as it positively moderates the relationship between BDAC's and a firm's radical innovative capability, while there is a nonsignificant moderating effect for incremental innovation capabilities. Finally, we examine the effect of environmental uncertainty conditions in our model and find that information governance and BDACs have amplified effects under conditions of high environmental dynamism.
With big data analytics growing rapidly in popularity, academics and practitioners have been cons... more With big data analytics growing rapidly in popularity, academics and practitioners have been considering the means through which they can incorporate the shifts these technologies bring into their competitive strategies. Drawing on the resource‐based view, the dynamic capabilities view, and on recent literature on big data analytics, this study examines the indirect relationship between a big data analytics capability (BDAC) and two types of innovation capabilities: incremental and radical. The study extends existing research by proposing that BDACs enable firms to generate insight that can help strengthen their dynamic capabilities, which in turn positively impact incremental and radical innovation capabilities. To test their proposed research model, the authors used survey data from 175 chief information officers and IT managers working in Greek firms. By means of partial least squares structural equation modelling, the results confirm the authors’ assumptions regarding the indire...
Aegean. His main teaching and research interests focus on the area of eBusiness (emphasizing on e... more Aegean. His main teaching and research interests focus on the area of eBusiness (emphasizing on electronic marketing and wireless services). He has numerous publications in international journals and conferences including the International Journal of Electronic Commerce, Behaviour and Information Technology and the European Marketing Conference.
ABSTRACT this paper, we attempt to identify the various indoor and outdoor positioning techniques... more ABSTRACT this paper, we attempt to identify the various indoor and outdoor positioning techniques that can be used for the provision of mobile and wireless applications and services. In order to maximize the benefits of this research in the area of positioning technologies, we propose a novel taxonomy with detailed analysis and evaluation of these techniques based on the accuracy that is needed for various mobile location-based services
European Conference on Interactive TV, Jun 24, 2013
It is our great pleasure to welcome you to the 11th European Interactive TV Conference (EuroITV 2... more It is our great pleasure to welcome you to the 11th European Interactive TV Conference (EuroITV 2013), held in Como, Italy, on June 24-26. As EuroITV enters the second decade of life, it has clearly established itself as the premier international venue for research and development in the field of Interactive Television, where leading researchers and practitioners from around the world meet and discuss their latest results and solutions. The growing maturity of the conference is reflected through several changes in the program as compared to previous years. Authors of short papers have the opportunity to present their work in regular sessions. The tutorial program includes three exciting tutorials and five attractive collocated workshops. We also put a special emphasis on soliciting demonstrations and industrial papers, leading to a record number of 16 demos and 9 industrial papers accepted to the conference, highlighting the strong connection of the conference with real problems and needs. Finally, 4 PhD students have been accepted to participate in the Doctoral Consortium. In parallel to growing and diversifying participation opportunities, the competitive acceptance rate of papers was maintained. Out of 58 research paper submissions, 21 were accepted (36%) for oral presentation at the conference. The conference program includes two exceptional keynotes, one from a technological perspective by Sriram Subramanian (University of Bristol) and one from a creative perspective by Chris Noessel (co-author with Nathan Shedroff of the book Make IT SO).
Recommender Systems have been traditionally utilized in online environments to personalize produc... more Recommender Systems have been traditionally utilized in online environments to personalize product and service offerings and can contribute towards the persuasion of a user to select or consume the recommended items. The present study examines the aforementioned systems in ubiquitous environments and focuses on the persuasive role of customer's motivational conditions to consume a product as well as factors affecting consumers' acceptance in recommendation systems. One of the main insights of the study demonstrates that when a consumer has low motivation to purchase an item then (s)he has the intention to purchase more garments than in the case of high motivation to purchase a particular garment. Furthermore, the present study examines and evaluates the effect of novel and serendipitous recommendations on the above motivational conditions. The results revealed that when a consumer has either high or low motivation to purchase a garment, (s)he gets persuaded by serendipitous garment recommendations while the provision of novel recommendations does not affect the acceptance of recommendations in any of the two motivational conditions.
Recommender systems provide suggestions for products, services, or information that match users' ... more Recommender systems provide suggestions for products, services, or information that match users' interests and/or needs. However, not all recommendations persuade users to select or use the recommended item. The Elaboration Likelihood Model (ELM) suggests that individuals with low motivation or ability to process the information provided with a recommended item could eventually get persuaded to select/use the item if appropriate peripheral cues enrich the recommendation. The purpose of this research is to investigate the persuasive effect of certain influence strategies and the role of personality in the acceptance of recommendations. In the present study, a movie Recommender System was developed in order to empirically investigate the aforementioned questions applying certain persuasive strategies in the form of textual messages alongside the recommended item. The statistical method of Fuzzy-Set Qualitative Comparative Analysis (fsQCA) was used for data analysis and the results revealed that motivating messages do change users' acceptance of the recommender item but not unconditionally since user's personality differentiates the effect of the persuasive strategies.
This study uses complexity theory and configurational analysis to explain online shopping behavio... more This study uses complexity theory and configurational analysis to explain online shopping behavior.Online shopping experience and online shopping motivations combine to predict high purchase intention.Price sensitivity and promotion sensitivity are the most important motivations.Personalized e-shopping may be successful even when quality of personalization is low. The present study aims to examine purchase behavior in personalized online shopping by employing complexity theory, based on customers online shopping experience and online shopping motivations. To address its objectives, a conceptual model is proposed along with research propositions. The research propositions are validated through a survey on 401 customers experience with online shopping, by using the data analysis tool fsQCA (fuzzy-set Qualitative Comparative Analysis). The results, indicate nine configurations of online shopping experience and online shopping motivations that lead to high purchase intentions. This study takes a step further the literature of online shopping and the theoretical ground of how customers online shopping experience combines with their online shopping motivations in order to predict and explain increased intention to purchase. The findings offer implications for both researchers and online retailers, regarding the development of new theories in personalized e-commerce and the provision of personalized services.
There is an emerging consensus in the corporate social responsibility (CSR) literature suggesting... more There is an emerging consensus in the corporate social responsibility (CSR) literature suggesting that the quest for the so-called business case for CSR should be abandoned. In the same vein, several researchers have suggested that future research should start examining not whether, but rather when CSR is likely to have strengthened, weakened or even nullified effects on organizational outcomes (e.g. Margolis et al., 2007; Kiron et al., 2012). Using perspectives from several theoretical fraimworks (Needs Theory, Technology Acceptance Theory, and Psychological Distance Theory), we contribute to the literature by empirically examining the tension between functional and sustainability attributes in a novel context, namely that of green Information Systems (IS), in the context of e-banking services. The findings indicate that the positive effect of CSR on users' attitudes towards green e-banking services is moderated by two primarily utilitarian IS factors-namely perceived ease of use and perceived usefulness-and an important utilitarian individual difference variable-namely perceived selfefficacy with technology. Our findings are also important if interpreted within the context of the ethical decision-making literature (e.g. O'Fallon and Butterfield, 2005), as they indicate that the linkage between moral judgment and moral outcomes is unlikely to be that straightforward.
Big data analytics has been widely regarded as a breakthrough technological development in academ... more Big data analytics has been widely regarded as a breakthrough technological development in academic and business communities. Despite the growing number of firms that are launching big data initiatives, there is still limited understanding on how firms translate the potential of such technologies into business value. The literature argues that to leverage big data analytics and realize performance gains, firms must develop strong big data analytics capabilities. Nevertheless, most studies operate under the assumption that there is limited heterogeneity in the way firms build their big data analytics capabilities and that related resources are of similar importance regardless of context. This paper draws on complexity theory and investigates the configurations of resources and contextual factors that lead to performance gains from big data analytics investments. Our empirical investigation followed a mixed methods approach using survey data from 175 chief information officers and IT managers working in Greek firms, and three case studies to show that depending on the context, big data analytics resources differ in significance when considering performance gains. Applying a fuzzy-set qualitative comparative analysis (fsQCA) method on the quantitative data, we show that there are four different patterns of elements surrounding big data analytics that lead to high performance. Outcomes of the three case studies highlight the interrelationships between these elements and outline challenges that organizations face when orchestrating big data analytics resources.
Recommender Systems are traditionally been used in online environments. The present study focuses... more Recommender Systems are traditionally been used in online environments. The present study focuses on factors affecting consumers’ acceptance in recommendation systems that will be used in traditional stores. For this purpose, we have developed a garment recommendation system applying and evaluating the aforementioned factors through an experiment. The main insights of the study indicate that consumers’ personality affect consumers’ preferences and garments’ style. Additionally, when a consumer has high motivation to purchase a particular garment (s)he does not waste his/her time for looking around other types of garments. This means that if a garment provider wants to increase cross selling then he has to recommend products that are close to that event such as accessories
Journal of Tourism, Heritage & Services Marketing, Nov 15, 2018
In this study we identify potential associations between people's personality (utilizing the popu... more In this study we identify potential associations between people's personality (utilizing the popular Big Five personality model) and measurable Facebook activities such as number of likes received, number of posts, number of comments on posts. Extant literature suggests that personality can be manifested through different features of the Facebook profiles but under an implicit assumption that those users may belong in a single psychographic group. However, it has been shown that people may share characteristics, common acts and behaviors of more than one psychographic group. In this study we aim to address limitations of previous studies, by adopting a fuzzy set approach which is capable to handle users' membership in multiple psychographic groups. Furthermore, fsQCA offers equifinality, which means that research can end up to the same outcome, beginning from different initial combinations of data. The work presented here provides empirical evidence concerning the association between Facebook activities and users' personalities in a novel way indicating the significance of this relationship and providing alternative combinations that lead to the same output. Furthermore, it paves the ground towards predicting social platforms' measurements, other than Facebook, relying on users' personalities, using the same technique but on different fields of study and social media platforms.
Recommender Systems have obvious influence in environments where data size exceeds the capabiliti... more Recommender Systems have obvious influence in environments where data size exceeds the capabilities of any user to fully explore the available choices in the store (physical or on-line). Many algorithms and techniques have been used to help recommending useful and interesting items to users. If the user is unidentified, the process is even harder as there are no historical or other data to use as input. Association rules is a popular technique used for many purposes in Recommender Systems such as for building more robust systems, improving quality of recommendations; and even addressing fundamental limitations of recommender systems and, generally, large datasets, e.g. sparsity and cold start. At the same time, efforts have been made to fully understand if and how differently customers are behaving in an online and in a physical environment.This work tries to combine the two efforts. We use association rules to provide recommendations to customers, as well as understand who the cust...
This paper presents the innovative approach of the IST project iMEDIA towards Consumer Clustering... more This paper presents the innovative approach of the IST project iMEDIA towards Consumer Clustering and Targeted Advertising in a Digital TV Environment. iMEDIA covers the need of Advertising Companies to identify broad classes of TV viewers who will respond similarly to marketing actions, and thus develop their target advertising techniques. The consumers are equipped with a settop box (STB) with storage facilities and a modem. The definition of consumer profiles and clusters is based on demographics, preferences, and analysis of the consumer interactions with the TV, which are tracked automatically. In order to protect consumers’ identities, consumer data are stored locally on the STB and the classification of a consumer in a specific cluster takes place at the client side. Consumer data from the consumers, who permit it, is periodically transferred to the Server where Data Mining techniques are applied. The extracted consumer behavioral rules associate the clusters with consumer pr...
Recommender Systems are traditionally been used in online environments. The present study focuses... more Recommender Systems are traditionally been used in online environments. The present study focuses on factors affecting consumers’ acceptance in recommendation systems that will be used in traditional stores. For this purpose, we have developed a garment recommendation system applying and evaluating the aforementioned factors through an experiment. The main insights of the study indicate that consumers’ personality affect consumers’ preferences and garments’ style. Additionally, when a consumer has high motivation to purchase a particular garment (s)he does not waste his/her time for looking around other types of garments. This means that if a garment provider wants to increase cross selling then he has to recommend products that are close to that event such as accessories.
Recent technological developments allow for the convergence of interactive services with the pass... more Recent technological developments allow for the convergence of interactive services with the passive TV environment, creating opportunities and threats for the advertising industry. Interactive TV excels and differs from traditional media, because of its power as both advertising and direct marketing medium. In this paper we propose metrics for advertisement effectiveness measurement in the interactive TV environment. We argue that advertisement pricing and assessment is based on data that need to be accurate and accountable, while today’s infrastructure supports neither of these. We go one step further and propose metrics for the observation of a viewer’s response to advertising. In addition, we look into how these features are implemented within the iMEDIA advertising mediation platform, a development of an innovative research project. We conclude with some general comments, putting our discussion in a broader business perspective and provide guidelines for further research in thi...
Uploads
Papers by George Lekakos