digging too much into the why’s or

INTRODUCTION TO BUSINESS predicting the future (prescriptive in nature).

ANALYSIS ❖ Business Analytics (BA) – deals with the
why’s of what happened in the past. It
Strategic business analysis breaks down contributing factors and
causality. It also uses these why’s to make
● Strategic Management is the predictions of what will happen in the future
(predictive in nature).
ongoing planning, monitoring,
analysis and assessment of all BUSINESS ANALYTICS
necessities an organization needs to
➔ Business analytics (BA) is the practice of
meet its goals and objectives.
repetitive, methodical exploration of an
● Strategic Business Analysis is the
organization’s data with emphasis on
process of gathering and analyzing statistical analysis. Business analytics is
data that helps a company’s leaders used by companies committed to data-driven
decide on priorities and goals, shaping decision making.
(or shifting) a long-term strategy for
the business. It gives a company the
ability to understand its environment,
and formulate a strategic plan
accordingly.
● Strategic Business Analysis requires
business intelligence and analytics,
which are data management solutions
implemented in companies and
enterprises to collect historical and
present data, while using statistics and HISTORY OF BUSINESS ANALYTICS
software to analyze raw information,
★ 5000 BC: Grog uses two sticks and four
and deliver insights for making better rocks to graph the upward trend in sales of
future decisions. his new invention, the wheel.
★ 1969: Woodstock ends in financial disaster
after organizers rely on spreadsheets to
estimate attendance.
ELEMENTS OF STRATEGIC ★ 1976: World gains sudden interest in the
BUSINESS ANALYSIS power of predictive analytics.
★ 1976-TO PRESENT: SAS is formed and
❖ Business Intelligence (BI) – deals with begins to give businesses The Power to
what happened in the past and how it Know.
happened leading up to the present moment.
It identifies big trends and patterns without
 Prescriptive analytics
● Recommends high-value alternative
actions or decisions given a complex set
of targets, limits, and choices.
NATURE OF ANALYTICS
● Predicts future outcomes and suggests
courses of actions to take so that you
can benefit from those predictions.

Advantages of business analytics

❖ ELIMINATE GUESSWORK
❖ GET FASTER ANSWER TO YOUR
QUESTION
❖ GET INSIGHT ABOUT BUSINESS
OPERATIONS
Descriptive Analytics ❖ IDENTIFY BUSINESS
➢ categorizes, characterizes, consolidates OPPORTUNITIES
and classifies data. ❖ GET KEY BUSINESS METRIC
➢ includes dashboards, reports (e.g., REPORTS WHEN AND WHERE THEY
budget, sales, revenue and costs) and ARE NEEDED
various types of queries.
➢ are most commonly applied to USERS OF BUSINESS ANALYTICS
structured data, although there have ★ Students
been numerous efforts to extend their ★ Businessman
reach to unstructured data, often ★ Accountants
through the creation of structured ★ Organization
metadata and indices. ★ Companies
➢ help provide an understanding of the ★ Group of industries
past as well as events occurring in ★ Small firm
real-time. ★ Auditors

Predictive Analytics Modern Software used for business

● Helps predict (based on data and analytics
statistical techniques) with confidence
what will happen next so that you can
➢ MS-EXCEL- Microsoft Excel is a
make well-informed decisions and
spreadsheet application developed by
improve business outcomes.
Microsoft for Microsoft Windows and
● This model is combined with historical
Mac OS. It features calculation,
data with rules, algorithms and other
graphing tools, pivot tables, and a
external data to predict the outcome or a
macro programming language called
situation.
Visual Basic for Applications.
● Uses simulation models to suggest what
➢ SPSS- SPSS Statistics is a software
could happen.
package used for statistical analysis.
 Long produced by SPSS Inc., it was
acquired by IBM in 2009. The current
versions (2014) are officially named IBM
SPSS Statistics.

CHALLENGES FOR BUSINESS

ANALYTICS
➔ Business analytics depends on sufficient
volumes of high quality data.
➔ The difficulty in ensuring data quality is
integrating and reconciling data across
different systems, and then deciding
what subsets of data to make available.
➔ Analytics was considered a type of
after-the-fact method of forecasting by
examining the historical data.
➔ This type of data warehousing required
a lot more storage space than it did
speed.
➔ The storage space for all that data must
react extremely fast to provide the
necessary data in real-time.
 Nature of Business relationships in data sets, with the purpose
of business improvement.
Analytics
Graphical/Tabular Descriptive Analytics - uses
THE NATURE OF BUSINESS the traditional and/or newer graphics to present
ANALYTICS easy-to-understand visual summaries of
Analytics is the use of: up-to-the-minute information concerning the
➢ data, operational status of the business.
➢ information technology,
➢ statistical analysis Numerical Descriptive Analytics - uses
➢ quantitative methods, and descriptive statistical tools to present
➢ mathematical or computer-based easy-to-understand numerical description of
models up-to-the-minute information concerning the
to help managers gain improved insight operstional status of the business. The analysis
about their business operations and includes association learning, text mining, cluster
make better, fact-based decisions. analysis, and factor analysis.

BUSINESS ANALYTICS Cluster Analysis - finding natural groupings or

APPLICATION clusters within data without having to prespecify a
● Management of customer set of categories.
relationships
● Financial and marketing activities Factor Analysis - involves starting with a large
● Supply chain management number of correlated variables and finding fewer
● Human resource planning underlying, uncorrelated factors that describe the
● Pricing decisions “essential aspects” of the large numbers of
correlated variables.

IMPORTANCE OF BUSINESS ANALYTICS

•There is a strong relationship of BA with: PREDICTIVE ANALYTICS
- profitability of businesses ❏ method used to predict values of a response
- revenue of businesses variable on the basis of one or more
- shareholder’s return predictor variables .
•BA enhances understanding of data
•BA is vital for businesses to remain ◦Parametric Predictive Analytics - Find a
competition mathematical equation that relates the response
•BA enables creation of informative reports variable to the predictor variable(s) and involves
unknown parameters that must be estimated and
SCOPE OF BUSINESS ANALYTICS evaluated by using sample data. Included tools such
DESCRIPTIVE ANALYTICS as classical linear regression, logistic regression,
❏ graphical/tabular and numerical methods discriminate analysis, neural networks, and time
used to find and visualize patterns, series forecasting.
associations, anomalies, and other
Nonparametric Predictive Analytics - makes DATA SOURCES
prediction by using a relationship between the Primary Data - collected by individual or business
response variable and the predictor variables that is directly from the source.
not expressed in tems of mathematical equation Secondary Data - taken from an existing source.
involving parameters. It inludes such tools as Data Warehousing - process of centralized
decision trees (classification or regression trees), management and retrieval and has its ideal objective
k-nearest neighbors, and naive Baye’s classification of creating and maintaining the central repository
for all the organization’s data.
Prescriptive Analytics Big Data - massive amounts of data, often collected
❏ techniques that combined external and at very fast rate in real time and in different forms.
internal constraints with results from
descriptive and predictive analytics. It DATA FOR BUSINESS ANALYTICS
includes decision theory methods, linear Examples of DATA in business:
optimization, nonlinear optimization, and ➢ Annual reports
simulation. ➢ Accounting audits
➢ Financial profitability analysis
➢ Economic trends
DATA FOR BUSINESS ANALYTICS ➢ Marketing research
Data - collected facts and figures ➢ Operations management performance
Data Set - data that are collected for particular ➢ Human resource measurements
study/problem
Data Elements - refer information about people, DATA IN BUSINESS ANALYTICS
objects, events, or other entities Metrics are used to quantify measurement.
Database - collection of computer files containing •Measures are numerical values of metrics.
data •Discrete metrics involve counting
Data Mining - process of discovering useful - number of people in a particular place
knowledge in extremely large data sets. - number or proportion of on time deliveries
Information - comes from analyzing data •Continuous metrics are measured on a continuum
- delivery time
VARIABLES - package weight
❏ characteristics or properties of the elements - purchase price
of the set of data
Example 1.2 A Sales Transaction Database File
◦Quantitative Variables- if the possible values are
numbers that represent quantities (how much, how
many)

◦Qualitative Variables - if the variable is

categorical in nature and the number assigned is just
used as its label
Four Types Data Based on Measurement Scale:
•Categorical (Nominal) Data
•Ordinal Data
•Interval data
•Ratio Data Interval Data
•Ordered data but with constant differences between
Example 1.3 Classifying Data Elements in a observations
Purchasing Database •No true zero point
•Ratios are not meaningful
•Examples:
- temperature readings
- SAT scores

DECISION MODEL
Model:
•An abstraction or representation of a real system,
Example 1.3 (continued) idea, or object
Classifying Data Elements in a Purchasing Database •Captures the most important features
•Can be a written or verbal description, a visual
display, a mathematical formula, or a spreadsheet
representation.

Categorical (Nominal) Data

•Data placed in categories according to a specified
characteristic
•Categories bear no quantitative relationship to one
another
•Examples:
- customer’s location (1 - America, 2 - Europe, 3-
Asia) ❏ A decision model is a model used to
- employee classification (manager, supervisor, understand, analyze, or facilitate decision
associate) making.

Ordinal Data •Types of model input

•Data that is ranked or ordered according to some - data
relationship with one another - uncontrollable variables
•No fixed units of measurement - decision variables (controllable)
•Without constant differences between ordered •Types of model output
observations - performance measures
•Examples: - behavioral measures
- college football rankings
- rank of honor students
NATURE OF DECISION MODEL TC is Total Cost
F is Fixed Cost
V is Variable Unit Cost
Q is Quantity produced

Example: A Break-even Decision Model

TC(manufacturing) = P50,000 + P125*Q
TC(outsourcing) = P175*Q
Descriptive Decision Models
•Simply tell “what is” and describe relationships Breakeven Point:
•Do not tell managers what to do Set TC(manufacturing)
= TC(outsourcing)
Example: An Influence Diagram for Total Cost Solve for Q = 1000 units
Influence Diagrams visually show how various
model elements relate to one another.

Example: A Linear Demand Prediction Model

As price increases, demand falls.
Example: A Mathematical Model for Total Cost

Example: A Nonlinear Demand Prediction Model

Assumes price elasticity (constant ratio of % change
in demand to % change in price)
TC = F +VQ
 For example, costs are too high compared with
competitors.

2. Defining the problem

❖ Clearly defining the problem is not a trivial
task.
❖ Complexity increases when the following
occur:
- large number of courses of action
- several competing objectives
- external groups are affected
Predictive Decision Models - problem owner and problem solver are not the
➢ often incorporate uncertainty to help same person
managers analyze risk. - time constraints exist
•Aim to predict what will happen in the future.
•Uncertainty is imperfect knowledge of what will 3. Structuring the problem
happen in the future. ❖ Stating goals and objectives
•Risk is associated with the consequences of what ❖ Characterizing the possible decisions
actually happens. ❖ Identifying any constraints or restrictions

Prescriptive Decision Models 4. Analyzing the problem

➢ help decision makers identify the best ❖ Identifying and applying appropriate
solution. Business Analytics (BA) techniques
•Optimization - finding values of decision variables ❖ Typically involves experimentation,
that minimize (or maximize) something such as cost statistical analysis, or a solution process
(or profit).
•Objective function - the equation that minimizes 5. Interpreting results and making a decision
(or maximizes) the quantity of interest. ❖ Managers interpret the results from the
•Constraints - limitations or restrictions. analysis phase.
•Optimal solution - values of the decision variables ❖ Incorporate subjective judgment as needed.
at the minimum (or maximum) point. ❖ Understand limitations and model
assumptions.
PROBLEM SOLVING AND DECISION ❖ Make a decision utilizing the above
MAKING information.
★ BA represents only a portion of the overall
problem solving and decision making 6. Implementing the solution
process. ❖ Translate the results of the model back to the
real world.
Six steps in the problem solving process ❖ Make the solution work in the organization
1. Recognizing the problem by providing adequate training and
❖ Problems exist when there is a gap between resources.
what is happening and what we think should
be happening.
 Descriptive Analytics: Tabular and
Graphical Methods

Summarizing And Describing Qualitative

And Quantitative Data Using Table

★ Frequency Distribution Table - table

that summarizes the number or
frequency of items in each several
non-overlapping classes.

Summarizing And Describing Qualitative

And Quantitative Data Using Graphs
➢ Histogram - a graphical display of data
using bars of different heights. A
histogram displays the shape and
spread of data.

TYPES OF BAR GRAPHS

❖ Stacked/Component Bar Graph

★ Cumulative Frequency Distribution -

The total frequency of all classes less
than the upper class boundary of a
given class.

❖ Compound Bar Graph

★ Relative Frequency Distribution -

summarizes the proportion or fraction of
items in each class.
Summarizing And Describing Qualitative ❖ Compound Line Graph
And Quantitative Data Using Graphs
➔ Frequency Polygon - is a graph
constructed by using lines to join the
midpoints of each interval. The heights
of the points represent the frequencies.

TYPES OF CIRCLE GRAPHS

❖ Pie Graph

➔ Ogive - known as a cumulative

frequency polygon, is a type of
frequency polygon that shows
cumulative frequencies. It is used to
estimate how many numbers lie below ❖ Doughnut Graph
or above a particular variable or value in
data.

TYPES OF LINE GRAPHS

❖ Simple Line Graph ❖ Exploded Pie Graph

❖ Ring/Sunburst/Multi-level Pie Graph

❖ Multiple Line Graph
❖ Spie Graph usage, "dashboard" is another name for
"progress report" or "report" and
considered a form of data visualization
in real time.

OTHER TYPES OF GRAPHS

★ Dots Plots

★ Stem-and-Leaf Display IMPORTANT NOTES

➢ The use of tables or graphs in
summarizing and describing the
characteristics of the sets of data
depends on the size, amount, and
volume of the data.
➢ The use of tables or graphs in
summarizing and describing the
characteristics of the sets of data should
★ Scatter Plots consider the classes or categories of
data.
➢ The use of tables or graphs in
summarizing and describing the
characteristics of the sets of data should
take into account the needs/purposes
that the data will serve or satisfy.
➢ The use of tables or graphs in
summarizing and describing the
MODERN TOOLS TO SUMMARIZE
characteristics of the sets of data should
AND DESCRIBE DATA help provide vivid representations of the
data.
➔ Dashboard - a type of graphical user
interface which often provides
at-a-glance views of key performance
indicators (KPIs) relevant to a particular
objective or business process. In other
 Descriptive Analytics: Numerical Standard Deviation - the point estimate of the
variance.
Method
● Population Standard Deviation (Ơ)
● Sample Standard Deviation (s)
DESCRIBING QUANTITATIVE DATA SETS
USING STATISTICAL TOOLS
Measure of Central Tendency - represents
the center or middle of the data.
★ Mean - the average of the
measurements of the data set.
Population Mean (µ)
Sample Mean (X)
Simple Mean
Weighted Arithmetic Mean (WAM)
★ Median (Md)- the measurement that NON-NORMAL DISTRIBUTION
divides the data set into two roughly Skewness - a distortion or asymmetry that
equal parts. deviates from the symmetrical bell curve, or
★ Mode (Mo)- the values in the normal distribution, in a set of data.
measurement that occurs frequently.

Measure of Variation - an estimate of the

variability of the values of the measurement.
★ Range - the difference between the Percentile - a value such that p percent of the
highest value and lowest value in the set measurements fall at or below the value and
of data. the (100- p) percent of the measurement fall at
★ Variance - the average of the squared or above the value for a set of measurements
deviations of the data sets. arranged in increasing order .
● Population Variance (Ơ2) Quartile - describes the variation of a set of
● Sample Variance (s2) measurement by dividing the set of data into
four equal parts.
Decile - describes the variation of a set of
measurement by dividing the set of data into
ten equal parts.
Interquartile Range - the difference between
the third and first quartile; the length of the
interval that contains the middle 50% of the
measurements.
Coefficient of Variation - measures the size
of the standard deviation of a population or
sample relative to the size of the population
mean or sample mean.
Covariance - measures the relationship
between two random variables and to what
extent they change together.

Spearman rho - measures the strength of the

relationship between two variables which are
continuous or ordinal in nature and have a
curvilinear, monotonic relationship.

Correlation Coefficient - measures the

strength of the linear relationship of two
variables that do not depend on the unit in
which the two variables are measured.
Pearson r - measures the strength of the
linear relationship between two variables and
their association with each other. It calculates
the effect of change in one variable when the
other variable changes
Kendall’s Coefficient - measures the ordinal
association between two measured quantities.
It is a non-parametric hypothesis test for
statistical dependence.

Chi-Square – a test of association which is

used to determine the association between two
categorical variables. It is considered as a
non-parametric test. It is mostly used to test
statistical independence.