12/6/2024

(Business) Analytics is the use of:

 data,
 information technology,
 statistical analysis,
 quantitative methods, and
 mathematical or computer-based models
to help managers gain improved insight about
their business operations and make better, fact-
based decisions. Business analytics is “a process of
transforming data into actions through
analysis and insights in the context of
Lecturer: Nguyen Van Dung Ph.D.
Slides are based on slides accompanied the book “Business Analytics:
organizational decision making and
Methods, Models, and Decisions”, with improvement from the lecturer problem solving.”

 Pricing
◦ setting prices for consumer and industrial goods, government  Business intelligence (collection, management,
contracts, and maintenance contracts analysis, and reporting of data)
 Customer segmentation
◦ identifying and targeting key customer groups in retail, insurance,
 Information Systems
and credit card industries  Statistics
 Merchandising  Operations research/Management science
◦ determining brands to buy, quantities, and allocations
 Location  Decision support systems
◦ finding the best location for bank branches and ATMs, or where to  Perhaps the most influential development in the
service industrial equipment
 Social Media use of business analytics have been the
◦ understand trends and customer perceptions; assist marketing personal computer and spreadsheet technology.
managers and product designers

 Benefits
◦ …reduced costs, better risk management, faster
decisions, better productivity and enhanced bottom-line
performance such as profitability and customer
satisfaction.
 Challenges
◦ …lack of understanding of how to use analytics,
competing business priorities, insufficient analytical skills,
difficulty in getting good data and sharing information,
and not understanding the benefits versus perceived
costs of analytics studies.

1
 12/6/2024

 Descriptive analytics: the use of data to Mean  Database queries and analysis
Min
understand past and current business Max
 Dashboards to report key performance measures
performance and make informed decisions S.D  Data visualization
 Predictive analytics (dự báo): predict the future  Statistical methods
by examining historical data, detecting, and then  Spreadsheets and predictive models
extrapolating (ngoại suy, suy luận ra) these  Scenario and “what-if” analyses
relationships forward in time.  Simulation
 Prescriptive analytics (Phân tích đề xuất):  Forecasting
identify the best alternatives to minimize (cost,  Data and text mining
distance, time) or maximize (profit, revenue) some
 Optimization
objective (optimization)
 Social media, web, and text analytics

Lí do dùng SPSS:
+ dễ dùng
+ mạnh

 Most department stores clear seasonal inventory  IBM Cognos Express

by reducing prices. ◦ An integrated business intelligence and planning solution
 Key question: When to reduce the price and by designed to meet the needs of midsize companies,
provides reporting, analysis, dashboard, scorecard,
how much to maximize revenue? planning, budgeting and forecasting capabilities.
 Potential applications of analytics:
 SAS Analytics
 Descriptive analytics: examine historical data for similar
products (prices, units sold, advertising, …) ◦ Predictive modeling and data mining, visualization,
forecasting, optimization and model management,
 Predictive analytics: predict sales based on price
statistical analysis, text analytics, and more.
 Prescriptive analytics: find the best sets of pricing and
advertising to maximize sales revenue  Tableau Software
◦ Simple drag and drop tools for visualizing data from
spreadsheets and other databases.

Dữ liệu sơ cấp (preliminary): tự thu

Dữ liệu thứ cấp (secondary): có sẵn
 Data: numerical or textual facts and figures that  Annual reports
are collected through some type of measurement  Accounting audits
process.  Financial profitability analysis
 Information: result of analyzing data; that is,  Economic trends
extracting meaning from data to support  Marketing research
evaluation and decision making.  Operations management performance
 Human resource measurements
 Web behavior
 page views, visitor’s country, time of view, length of time, origin
and destination paths, products they searched for and viewed,
products purchased, what reviews they read, and many others.

2
 12/6/2024

A database file is usually organized in a two-

dimensional table, where the columns
correspond to each individual element of data
 Data set - a collection of data. (called fields, or attributes), and the rows
◦ Examples: Marketing survey responses, a table of represent records of related data elements.
historical stock prices, and a collection of measurements
of dimensions of a manufactured item.
 Database - a collection of related files containing
records on people, places, or things.
◦ A database for an online retailer sells instructional fitness Records
books and DVDs, for instance, might consist of a file for
three entities: publishers from which goods are
purchased, customer sales transactions.

Entities Fields or Attributes

 Big data to refer to massive amounts of business data  Metric (đơn vị đo lường) - a unit of measurement
from a wide variety of sources, much of which is that provides a way to objectively quantify
available in real time, and much of which is uncertain or performance.
unpredictable. IBM calls these characteristics volume,
variety, velocity, and veracity.  Measurement (sự đo lường) - the act of obtaining
 “The effective use of big data has the potential to data associated with a metric.
transform economies, delivering a new wave of  Measures (giá trị đo lường ra) - numerical values
productivity growth and consumer surplus. Using big associated with a metric.
data will become a key basis of competition for existing
companies, and will create new competitors who are
able to attract employees that have the critical skills for a
big data world.” - McKinsey Global Institute, 2011

 Discrete (rời rạc) metric - one that is derived

from counting something.  Categorical (phân loại)/ (nominal) (định danh) data
◦ For example, a delivery is either on time or not; an order - sorted into categories according to specified
is complete or incomplete; or an invoice can have one, characteristics.
two, three, or any number of errors. Some discrete  Example: a firm’s customers might be classified by their
metrics would be the proportion of on-time deliveries; the geographical region (North America, South America, Europe,
number of incomplete orders each day, and the number and Pacific)
of errors per invoice.  Ordinal (thứ tự) data - can be ordered or ranked
 Continuous metrics are based on a continuous according to some relationship to one another.
scale of measurement.  Example: Rating a service as poor, average, good, very good,
◦ Any metrics involving dollars, length, time, volume, or or excellent
weight, for example, are continuous.

3
 12/6/2024

 Ordinal data have no fixed units of measurement ==> cannot  Interval (khoảng) data - ordinal but have
make meaningful numerical statements about differences constant differences between observations
between categories. We cannot say that the difference
and have arbitrary zero points.
between excellent and very good is the same as between
good and average.  Examples are time and temperature. Time is relative to
global location, and calendars have arbitrary starting
dates.
 Both the Fahrenheit and Celsius scales represent a
specified measure of distance—degrees—but have no
natural zero. Thus we cannot take meaningful ratios; for
example, we cannot say that 50 degrees is twice as hot
as 25 degrees

 Ratio (tỷ lệ) data - continuous and have a natural

zero.
 For example, the measure dollars has an absolute zero.
Ratios of dollar figures are meaningful. For example,
knowing that the Seattle region sold $12 million in March
whereas the Tampa region sold $6 million means that
Seattle sold twice as much as Tampa.
 This classification is hierarchical in that each
level includes all the information content of the
one preceding it.

Copyright © 2016 Pearson Education, Inc.

publishing as Prentice Hall 1-23

 Reliability (Ổn định/tin cậy) - data are accurate and consistent.

 Validity (Chuẩn xác) - data correctly measures what it is
supposed to measure.
 Examples:
◦ A tire pressure gage that consistently reads several pounds of pressure
below the true value is not reliable, although it is valid because it does
measure tire pressure.

4
 12/6/2024

 Examples:  Examples:
◦ The number of calls to a customer service desk ◦ A survey question that asks a customer to rate the
might be counted correctly each day (and thus is a quality of the food in a restaurant may be neither
reliable measure) but not valid if it is used to assess reliable (because different customers may have
customer dissatisfaction, as many calls may be simple conflicting perceptions) nor valid (if the intent is to
queries. measure customer satisfaction, as satisfaction
generally includes other elements of service besides
food).

The sales of a new product, such as a first-generation iPad or

 Model - an abstraction or representation of a real 3D television, often follow a common pattern.
system, idea, or object.
 Captures the most important features 1. Verbal description: The rate of sales starts small as early
 Can be a written or verbal description, a visual adopters begin to evaluate a new product and then begins
representation, a mathematical formula, or a to grow at an increasing rate over time as positive
spreadsheet. customer feedback spreads. Eventually, the market
begins to become saturated (bão hòa) and the rate of
sales begins to decrease.

2. Visual model: A sketch of sales as an S-shaped curve

over time 3. Mathematical model: S = aebect
where S is sales, t is time, e is the base of natural
logarithms, and a, b and c are constants.

5
 12/6/2024

 Influence diagram - a visual representation of a

descriptive model that shows how the elements of
the model influence, or relate to, others.
 An influence diagram is a useful approach for
conceptualizing the structure of a model and can assist in
building a mathematical or spreadsheet model.

Basic Expanded

 total cost = fixed cost + variable cost (1.1)  Decision model - a logical or mathematical
 variable cost = unit variable cost × quantity produced representation of a problem or business situation that
(1.2) can be used to understand, analyze, or facilitate making
 total cost = fixed cost + variable cost
a decision.
= fixed cost + unit variable cost × quantity produced
(1.3)  Inputs:
◦ Data, which are assumed to be constant for purposes of the
model.
Mathematical model: ◦ Uncontrollable variables, which are quantities that can change but
 TC = Total Cost cannot be directly controlled by the decision maker.
 F = Fixed cost ◦ Decision variables, which are controllable and can be selected at
 V = Variable unit cost the discretion of the decision maker.
 Q = Quantity produced
 TC = F +VQ (1.4)

TC(manufacturing) = $50,000 + $125*Q

TC(outsourcing) = $175*Q
Breakeven Point: TC(manufacturing) = TC(outsourcing)

$50,000 + $125 × Q = $175 × Q

$50,000 = 50 × Q
Q = 1,000

 General Formula
F + VQ = CQ
Q = F/(C - V) (1.5)

6
 12/6/2024

 In the grocery industry, managers typically need to know  Grocers often study the relationship of sales volume to
how best to use pricing, coupons and advertising these strategies by conducting controlled experiments
strategies to influence sales. to identify the relationship between them and sales
volumes.

 That is, they implement different combinations of

pricing, coupons, and advertising, observe the sales
that result, and use analytics to develop a predictive
model of sales as a function of these decision
strategies.

 Assumptions are made to

◦ simplify a model and make it more tractable; that is, able to be
easily analyzed or solved.
◦ better characterize historical data or past observations.
 The task of the modeler is to select or build an
appropriate model that best represents the behavior of
Sales = 500 – 0.05(price) + 30(coupons) + 0.08(advertising) + the real situation.
0.25(price)(advertising)
 Example: economic theory tells us that demand for a
If the price is $6.99, no coupons are offered, and no advertising is done product is negatively related to its price. Thus, as prices
(the experiment corresponding to week 1), the model estimates sales as increase, demand falls, and vice versa (modeled by
price elasticity — the ratio of the percentage change in
Sales = 500 - 0.05 × $6.99 + 30 × 0 + 0.08 × 0 + 0.25 × $6.99 × 0 =
demand to the percentage change in price).
500 units

Assumes price elasticity is constant (constant ratio of

As price increases, demand falls. % change in demand to % change in price)

7
 12/6/2024

 Uncertainty is imperfect knowledge of what will happen

in the future.  Prescriptive (đề xuất) decision models help
 Risk is associated with the consequences of what decision makers identify the best solution.
actually happens.  Optimization - finding values of decision variables
 “To try to eliminate risk in business enterprise is futile (vô that minimize (or maximize) something such as
ích). Risk is inherent in the commitment of present cost (or profit).
resources to future expectations. Indeed, economic  Objective function - the equation that minimizes (or
progress can be defined as the ability to take greater maximizes) the quantity of interest.
risks. The attempt to eliminate risks, even the attempt to  Constraints - limitations or restrictions.
minimize them, can only make them irrational and  Optimal solution - values of the decision variables at the
unbearable. It can only result in the greatest risk of all: minimum (or maximum) point.
rigidity.”
– Peter Drucker

 A firm wishes to determine the best pricing for one  Deterministic model (Mô hình tất định) – all
of its products in order to maximize revenue. model input information is known with certainty.
 Analysts determined the following model:  Stochastic model (Mô hình ngẫu nhiên) – some
Sales = -2.9485(price) + 3240.9 model input information is uncertain.
Total revenue = (price)(sales) ◦ For instance, suppose that customer demand is an
= price × (-2.9485 × price + 3240.9) important element of some model. We can make the
assumption that the demand is known with certainty; say,
= 22.9485 × price2 + 3240.9 × price 5,000 units per month (deterministic). On the other hand,
suppose we have evidence to indicate that demand is
 Identify the price that maximizes total revenue, uncertain, with an average value of 5,000 units per
subject to any constraints that might exist. month, but which typically varies between 3,200 and
6,800 units (stochastic).

1. Recognizing a problem Problems exist when there is a gap between what is

2. Defining the problem happening and what we think should be happening.
3. Structuring the problem  For example, costs are too high compared with

4. Analyzing the problem competitors.

5. Interpreting results and making a decision
6. Implementing the solution

8
 12/6/2024

 Clearly defining the problem is not a trivial (tầm  Stating goals and objectives
thường) task.
 Characterizing the possible decisions
 Complexity increases when the following occur:
- large number of courses of action  Identifying any constraints or restrictions
- the problem belongs to a group and not an
individual
- competing objectives
- external groups are affected
- problem owner and problem solver are not the
same person
- time limitations exist

 Analytics plays a major role.  Models cannot capture every detail of the real
 Analysis involves some sort of experimentation or problem
solution process, such as evaluating different  Managers must understand the limitations of
scenarios, analyzing risks associated with various models and their underlying assumptions and
decision alternatives, finding a solution that meets often incorporate judgment into making a decision.
certain goals, or determining an optimal solution.

 Translate the results of the model back to the real www.puzzlOR.com

world.  Maintained by an analytics manager at ARAMARK.
 Requires providing adequate resources,  Each month a new puzzle is posted.
motivating employees, eliminating resistance to  Many puzzles can be solved using techniques you
change, modifying organizational policies, and will learn in this book.
developing trust.  The puzzles are fun challenges.
 A good one to start with is SurvivOR (June 2010).
 Have fun!