Analyze the Data: Exploratory Business Analytics

Because learning changes everything.®
Introduction to
Business Analytics
© 2022 McGraw Hill. All rights reserved. Authorized only for instructor
use in the classroom. No reproduction or further distribution permitted
without the prior written consent of McGraw Hill.
1
© McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC.

Analyze the Data:
Exploratory Business
Analytics
(Descriptive and Diagnostic Analytics)
Chapter 4
2
© 2022 McGraw Hill. All rights reserved. Authorized only for instructor use in the classroom. No reproduction or further distribution permitted without the prior written consent of McGraw Hill.

Because learning changes everything.®
4.1
Explain where ‘Analyze the Data’
fits in the SOAR analytics model.
4.2
Describe the five types of data
analytics: descriptive, diagnostic,
predictive, prescriptive, and
adaptive/autonomous analytics.
4.3
Define exploratory analytics and
confirmatory analytics.
4.4
Define descriptive analytics and
enumerate its various techniques.
4.5
Define diagnostic analytics and
describe its techniques.
4.6
Describe and use the techniques
in Excel’s Data Analysis Toolpak.
3

Explain where
‘Analyze the Data’
fits in the SOAR
Analytics Model
LO 4.1
4

The SOAR Analytics Model
1. Specify the Question
2. Obtain the Data
3. Analyze the Data
4. Report the Results
EXHIBIT 4.1 The SOAR Analytics Model
5

Progress Check 4.1
Q: Is “Analyze the Data” done before
or after finding the appropriate data to
address the question? Why?
6

Describe the Five
Types of Analytics
LO 4.2
7

8
Five Questions – Five
Analytics Types
 There are all sorts of business questions we could and ask, but
we can group most of them into these five types of relatively
simple questions that correspond to the five types of analytics:
 Descriptive Analytics: What happened? What is happening?
 Diagnostic Analytics: Why did it happen? What are the causes
for past results? Why are results different than expectations?
 Predictive Analytics: Will it happen in the future? What is the
probability something will happen? Can we forecast what will
happen?
 Prescriptive Analytics: What should we do, based on what we
expect will happen? How do we optimize our performance
based on potential constraints?
 Adaptive Analytics: How can we continuously learn using
artificial intelligence? Can we learn from past and current
events with adaptive learning?

9
Descriptive Analytics – What
Happened?
Marketing Operations Accounting Finance
Descriptive
Analytics
What
happened?
What is
happening?
• How many
units were sold
in the period?
By region? By
store?
• What was the
average
revenue for
each month?
• What are the
top 10 products
in terms of
sales and
profit?
• How many web
page views
resulted in a
sale?
• What is the
customer fill rate?
• What is the
average supplier
lead time?
• What is the
average customer
service level?
• What is the
annual employee
turnover rate?
What division has
the highest
turnover rate?
• What is our
average time-to-
fill (an employee
position)?
• How much did
we pay in federal
taxes last year?
• Which product is
the most
profitable one for
the company?
• What is the
balance of
inventory on
hand?
• What is the
effective tax rate
paid?
• How big is the
difference
between taxable
income and net
income?
• What are the
descriptive
performance
statistics (e.g.,
means,
medians,
maximums
and
minimums) for
the retail
industry?
• What was the
Return on
Asset, Asset
Turnover,
Return on
Profits ratios
last year?

10
Diagnostic Analytics – Why
did it Happen?
Diagnostic
Analytics
Why did it
happen?
What are the
reasons for past
results?
Can we explain
why it happened?
• Why did
revenue
change?
• Why did web
page views
change?
• Why did the
click-through
rate change
from last
month to this
month?
• Why did customer
fill rate change?
• Why did average
supplier lead time
change?
• Why did average
customer service
level change?
• Why has employee
turnover changed?
• Why has time-to-
fill changed?
• Why is revenue up
on the west coast
but down in the
Midwest?
• Why did SG&A
(sales, general and
administrative)
costs increase as
compared to the
industry?
• Why is the
difference between
taxable income and
net income getting
bigger?
• Why did the
interest rate
increase for the
company overall?
• Why did overall
income tax
increase even
though net
income did not?
• Why did stock
returns increase
last year in the
U.S. as compared
to China?
• Why did bond
prices fall?

11
Predictive Analytics – What is
Likely to Happen in the Future?
Predictive
Analytics
Will it
happen in
the future?
What is the
probability
something
will happen?
Is it
forecastable
?
• What will
product sales
(and units) be?
• What will web
page views be?
• Does the
weather
predict sales of
certain
products?
• Can we forecast
demand for our
new product?
• What happens if
the company
changes its
inventory policy
(e.g., order
quantity)?
• How long will an
employee stay
with the
company?
• What will the
demand for our
products be
based on new
products from our
competitors?
• Can we forecast
future
revenues/cash
flows/earnings
with reasonable
accuracy?
• Can we predict if
the financial
statements
might be
misstated or
might be
fraudulent?
• What is the
chance the
company will
go bankrupt?
• Do we extend
credit or not to
customers
based on
customer
characteristics
(credit score,
payment
history,
existing debt,
etc.)?

12
Prescriptive Analytics – What
action should we take?
Prescriptive
Analytics
What should we
do, based on
what we expect
will happen?
How do we
optimize our
performance
based on
potential
constraints?
• What
product
recommend
ations might
increase
conversion
rates?
• How can we
improve
customer
sentiment?
• What is the optimal
inventory policy to
maintain a specified
item fill rate? What is
the optimal level of
production?
• What is the optimal
scheduling policy?
• What is the best
delivery route (in terms
of costs and time)?
• Where should the
warehouses be
located?
• How many employees
are needed for the
summer season?
• Which employees need
to go to training to
improve productivity
(before productivity
declines or depart)?
• Should the
company buy or
lease their
headquarters
office building?
• Should the
company make its
products or
outsource to other
producers?
• What is the level of
sales that will
allow us to
breakeven?
• What is optimal
for the company?
Move its
operations to
Ireland to
minimize taxes or
stay in the USA?
• Should the
company move
operations to
Ireland to
minimize taxes?
• How will our
taxes change if
certain tax laws
change in the
next U.S.
Congress
legislative
section?
• What is the
optimal
investment: Real
estate, stocks or
bonds?

13
Adaptive/Autonomous Analytics –
How can we continuously learn?
Prescriptive
Analytics
How can we
continuously
learn using
artificial
intelligence?
How can we
learn from past
and current
events with
adaptive
learning?
• Is our
current
marketing
campaign
working?
How should
we adjust
our strategy
today?
• How should
we adjust
our strategy
given the
way we
expect the
competition/
industry to
change?
• How do we
continuously update
our predictions of
needed inventory to
more closely meet
customer demand?
• Could a computer
learn from the
decisions of the
internal audit
departments
which transactions
might constitute
fraud (and require
further
investigation)?
• Can the
company
rebalance its
investment
portfolio to
optimize its
portfolio based
on the change in
oil prices last
week?
• What
opportunities do
changes in the
exchange rates
for foreign
currencies
present?

Progress Check 4.2
Q. How is the investigation of which
product recommendations affect conversion
rates (getting interested observers to actually
buy the products rather than just read
reviews) be an example of prescriptive
analytics instead of diagnostic or predictive
analytics?
14

Define
Exploratory Data
Analytics
LO 4.3
15

16
Exploratory Data Analytics
 Exploratory data analytics as initial descriptive and
diagnostic data analytics investigations to summarize
and explain performance and activity.
 Exploratory analytics explores the data and begins to
generate questions and hypotheses that need further
explanation.
 Exploratory data analytics includes the practice of
exploring the data by summary performance statistics,
anomaly identification, and pattern detection.
 Confirmatory Data analytics are predictive and
prescriptive analytics that use statistics to judge the
likelihood (probability) of a future event or outcome
occurring.

Descriptive
Analytics
LO 4.4
17

18
Define Descriptive Analytics
 Descriptive analytics addresses the questions of “What
happened?” or “What is happening?”.
 We define descriptive analytics as analytics
performed which characterizes, summarizes, and
organizes features and properties of the data to
facilitate understanding of the results and the
underlying data.

19
Business Data Sources to
Consider in Descriptive Analytics
 Human Resource Management Systems (HRMS)
 Customer Relationship Management Systems (CRM)
 Supply Chain Management Systems (SCM)
 Financial Reporting (Accounting) Systems (FRS)

20
Human Resource
Management Systems
 A human resource management system (HRMS) is
an information system for managing all interactions
with current and potential employees.
 Data Included:
 Recruiting data and leads
 Employee training (current and desired certifications)
 Payroll and compensation (including tax elections like
401k contributions, # of dependents, amount of state
and federal withholding, etc.)
 Employee benefits (stock options, bonuses, health
insurance, etc.)

21
Customer Relationship
Management System
 A customer relationship management (CRM)
system is an information system for managing all
interactions with current and potential customers.
 Data Included:
 Customer contact history:
 What happened in the interaction (what they asked about
or what was decided)?
 Any interest in new products or services?
 Customer order history.
 Customer level of trade discounts or payment terms.
 Customer credit score (is their credit improving or
declining?).

22
Supply Chain Management
Systems
 A company’s supply chain is the sequence of
processes to get a good or product from original
production to final customer delivery.
 The system used to track those supply chain
processes is called supply chain management
systems.
 Data includes:
 active vendors (their contact info, where payment
should be made, how much should be paid),
 the orders made to date (how much, when the orders
are made), or
 demand schedules for what component of the final
product is needed when and where.

23
Financial Reporting Systems
 Financial reporting systems (FCS), or accounting
systems, are systems that capture and measure
financial transactions and communicate financial
performance to interested parties.
 Financial statements are collection of reports that
communicate a company’s financial results, financial
condition, financial health and its cash flows.

Descriptive Analytics
Techniques
24
 What would you use to address the questions of
“What happened?” or “What is happening?”.
 What would you use to “characterize, summarize, and
organize” what happened?

Descriptive Analytics
Techniques
 Mean, Median, Mode
 What is the average
employee salary? What is
the average stock market
return over the past five
years?
 Minimums, Maximums
 What are the descriptive
performance statistics (e.g.,
means, medians,
maximums and
minimums) for the retail
industry last year?
 Standard Deviation
 What is the standard
deviation of the company’s
stock price over the last
quarter?
 Quartiles/Deciles
 What quartile is Ford in
based on its leverage
compared to the
automobile industry as
a whole?
 Counts
 How many sales
transactions did we
have last year?
 Totals, Sums, Subtotals
supplier lead time?
customer service level?
25

More Descriptive Analytics
Techniques
Graphs (Bar Charts)
What is our average time-to-fill an
employee position over time? And
how has that changed over time?
Percentage Change
What is the percentage increase
in sales, general and
administrative expenses from last
year to this year?
PivotTables
What is the total profitability of
each customer or each inventory
item?
Histogram
What is the frequency of aged
receivables in each 30-day
bucket?
Ratio Analytics
The computation of the debt-
to-equity ratio as a measure of
solvency.
Vertical Analysis
The comparison of interest
expense in relation to net sales
revenue from one period to
the next.
Horizontal Analysis
What is the percentage
increase in accounts
receivable from the prior
balance to the current balance
sheet?
26

Descriptive Statistics
(From Excel Data Analysis Toolpak)
EXHIBIT 4.4 Descriptive Statistics for Exotic Fruits (From Lab 4.1 Excel)
27

28
Horizontal Analysis
Horizontal analysis is a descriptive analysis technique that
calculates and displays the dollar and percentage change in
financial statement line items from one period to the next.
Exhibit 4.6 Horizontal Analysis for Tyson Foods Inc. Income Statement

29
Vertical Analysis
Vertical analysis examines financial performance over a period of
time by expressing financial information in relation to some
relevant figure, or base.

Diagnostic
Analytics
LO 4.5
30

Define Diagnostic Analytics
 Diagnostic analytics is performed to investigate the
underlying reasons for past results that cannot be
answered by simply looking at the descriptive data.
31

Define Diagnostic Analytics
 Diagnostic analytics is broken down into two broad
categories to help determine “Why Something
Happened?”:
 Identifying Anomalies and Outliers
 Finding Previously Unknown Linkages, Patterns, or
Relationships between Variables
 Performing Drill-Down Detailed Analytics
 Performing Statistical Analyses
32

33
Identifying Anomalies and
Outliers
 Sometimes analysts use diagnostic analytics to help
find an anomaly, which is something that departs, or
deviates, from the expected, or the norm. In many
ways, an outlier is similar to an anomaly, it is an
observation, or a data point, that lies outside its
expected distribution. It could just be a mistake, or
the result of a fraud or it could be truth.
 To detect an anomaly or an outlier, it is important to
establish the norm, or the expectation.

© 2022 McGraw Hill. All rights reserved. Authorized only for instructor use in the classroom. No
reproduction or further distribution permitted without the prior written consent of McGraw Hill. 34
Identifying Anomalies and
Outliers: What’s the Expectation?
Branch of
Business
The Business Analysts’
Expectation
Example of Anomaly Possible Explanation for
the Anomaly/Outlier
Marketing The increase in sales is
roughly equivalent to
the increase in sales for
other companies in the
same industry
Our companies’ sales grew
at twice the rate of our
competitor.
New products sold
particularly well, causing
an increase in sales greater
than the competition
Operations The employee turnover
rate will be roughly
equivalent to the rate
experienced last year by
our company.
The employee turnover is
25% higher than what the
company experienced last
year.
Other businesses in the
workplace are in need of
skilled workers and are
offering higher
compensation packages
due to their unique skills.
Accounting Accountants record
transactions in
conformity with
Generally Accepted
Accounting Principles
(GAAP)
PwC found its client
capitalized rather than
expensing R&D
expenditures, contrary to
GAAP.
The company bought
testing equipment for
future R&D projects.
Should it be capitalized?
Finance Our company’s bond
prices are priced just
lower than the U.S.
government treasury
yields.
Our company’s bond
prices fell in relation to the
U.S. government treasury
yields.
Due to poor financial
performance, our bonds
were graded as risky, thus
lowering the bond price.

35
Diagnostic Techniques to Find
Anomalies
Technique Expectation Potential Anomaly How Test Works to Identify Anomaly
Cash/Bank
Reconciliation
All cash transactions
recorded by the company
are also recorded by the
bank.
Some cash transactions are
recorded by the company
or by the bank but not
both.
Conditional formatting or Excel Match ()
commands highlights transactions not
recorded by both (Illustrated in Lab 4.2).
Bank reconciliations are used to make
sure all transactions are recorded
properly.
Benford’s Law As part of Benford’s law,
the first digit of naturally
occurring numerical
datasets follow an
expected distribution.
The leading digit of some
naturally occurring
datasets does not follow
the expected distribution
suggesting something that
requires further
investigation.
The test of Benford’s Law compares first
digits of numbers in the dataset to first
digits of numbers expected by Benford’s
Law (Illustrated in Lab 4.3). Benford’s Law
is often used to identify fraud.
Testing for
Duplicate
Transactions
Each transaction is
recorded once and only
once.
Each transaction is
sometimes duplicated,
leading to errors.
Duplicate transaction test looks for the
same amount recorded two or more
times in order to correct possible errors.
Fuzzy Matching Different names represent
different individuals.
Different addresses
represent different
locations.
Although names or
addresses might not be
exactly the same, they
actually represent the same
person.
Fuzzy matching attempts to find a match
which, although not a 100 percent match,
is above the threshold matching
percentage set by the application
(Illustrated in Lab 9-1).

Benford’s Law – Theoretical
Distribution of the First Digit of a
Set of Naturally Occurring
Numbers
36

Actual vs. Expected Distribution of
First Digits – Can It Identify Fraud?
37

Benford’s Law
 What’s the benchmark?
 What’s the outlier?
 What’s the anomaly?
38

39
Diagnostic Analytics to Find Previously
Unknown Linkages, Patterns, or
Relationships between Variables
 Performing Drill-Down Detailed Analytics –
By looking for patterns in the underlying
data set or an external data set, we can
identify potential correlations. Drill-down
analytics works to summarize data at
different levels and uncover additional details
to understand why something happened.
 Performing Statistical Analyses– This
category of data analytics works to uncover
statistical patterns in the data, or how data
moves together.

Moneyball!
 The movie starring Brad Pitt tells the true story of
finding patterns to identify undervalued talent for the
Oakland Athletics in Major League Baseball.
 This is an example of using analytics to find previously
unknown patterns.
40

Drill-Down Tools/Techniques
Used in Diagnostic Analytics
 Drill into the analytics to help explain why or how something has
occurred:
 Analysis of the Highest Owing Customer: Which
customers included in the total accounts receivable owing
have the highest balances outstanding? Do some accounts
need to be written off due to uncollectibility?
 Analysis of the Most Profitable Customer: By learning
which customers are most profitable, the company can
better work and cater to these customers.
 Analysis of the Most Profitable Product: By learning which
products are most profitable, the company can better
promote them to their customers. At the same time, they
will be learning which products are not profitable and either
work to make them more profitable (raise sales price, get
product from another cheaper source), or just cut them from
their offering altogether.
41

42
Statistical Analysis

Hypothesis Testing
Hypothesis Testing using a Difference in Means:
 Are mean production cycle times in the Phillipines the
same or different from mean production cycle times
in Vietnam?
Hypothesis Testing using Regression:
 Is employee turnover associated with rapidly rising
wages in the economy?
43

Progress Check 4.5
Q. You’ve developed a hypothesis
that it is faster to source artificial
Christmas trees from Indonesia (to
Seattle) than from the Philippines
(to Seattle).
Using statistical analysis, how
would you test that hypothesis?
Why is this an example of
diagnostic analytics?
44

Introduction to
the Data Analysis
Toolpak (Excel)
LO 4.6
45

46
Excel’s Data Analysis Toolpak
Offers a Variety of Analytics Tools
EXHIBIT 4.17 Analytics Techniques Available within the Data Analysis Toolpak

47
Some Available Techniques in
Excel’s Data Analysis Toolpak
 Correlation: To understand if and the extent to which variables are
related to each other
 Descriptive statistics: To understand the basic statistics, including
the mean (average), standard deviation, and minimums and
maximums, of a data set
 Histogram: To understand the frequency of the data using a display
of rectangles whose areas are proportional to the underlying
frequency of the data
 Regression: To understand the relationship between specific inputs
and outputs
 t-test: To understand the probability of a statistical difference in
averages between two independent samples or between a paired
sample through time

48
Progress Check 4.6
Q. Which data analysis toolpak
technique would be use to test if
sales at one store are statistically
greater than sales at another
store?

Labs Associated with Chapter
4
Lab # Lab Name
4.1
Excel: Evaluating Inventory Using Inventory Turnover,
Waste and Profit Margins
4.2
Excel: Using Conditional Formatting to Perform a Bank
Reconciliation
4.3 Excel: Applying Benford’s Law

Analyze the Data: Exploratory Business Analytics

More Related Content

Similar to Analyze the Data: Exploratory Business Analytics (20)

Recently uploaded (20)

Analyze the Data: Exploratory Business Analytics