Introduction to

Accounting Analytics
DATA ANALYTICS IN ACCOUNTING AND
BUSINESS
A D A P T E D F R O M M C G R AW - H I L L E D U C AT I O N . P L E A S E D O N OT D I S T R I B U T E .

Instructor: Huijue Kelly Duan

Learning Objectives
▪ Define Data Analytics.
▪ Understand why Data Analytics matters to business.
▪ Explain why Data Analytics matters to accountants.
▪ Describe the Data Analytics Process using the IMPACT cycle.
▪ Describe the skills needed by accountants.

2
Learning Objective 1

What is data analytics?

3
Data Analytics
Data – are raw figures and facts

Information – uses technology to transform data into knowledge

Data Analytics is the process of evaluating data with the purpose of

drawing conclusions to address business questions.
• Effective Data Analytics provides a way to search through large
structured and unstructured data to identify unknown patterns or
relationships.
 Big Data
Big Data refers to datasets which are too large and complex to be
analyzed traditionally.

Remember the 5V ’s:

•Volume refers to size
•Variety refers to different types
•Velocity refers to frequency/Speed
•Veracity refers to the data quality (reliability/integrity)
•Value refers to the benefits the data provides

5
Data Volume
Why is Data Growing Exponentially?

1. Technologies are connecting and

integrating data from traditionally
separate systems, such as the AIS,
1. Technologies are connecting and integrating data from
internet content,
traditionally separate systems,and smart
such as the AIS, internetdevice
content,
and smart device sensors.
sensors.
2. Decreasing computer costs and increasing computer memory
and processing capabilities make it easier for organizations to
capture, store, and analyze more data.

2. Decreasing computer costs and

increasing computer memory and
processing capabilities make it
easier for organizations to capture,
store, and analyze more data.

6
Comparing Cloud
Data Services
HP Enterprise,
VMWare,
Microsoft, Cisco,
and Amazon.
Benefits of Cloud
Data Services:
• Storage capacities Google Cloud Platform,
• Data management Amazon Web Services
• Data securities
(AWS), and Microsoft
• Expert support
Azure.

Leading Vendors:
Amazon and
Microsoft.

7
Data Variety
• Data variety refers to the diversity of data structures and
measurement scales in the data we want to analyze.

• Accountants are evolving from the traditional focus of selecting and

analyzing structured data that are easily represented in rows and
columns.

• Accountants are combining structured data with unstructured data,

including text, smart device sensor readings, and pictures and
graphics, to increase the value created from their analyses.
 Examples of Combining Data

Shipping truck GPS Integrating GPS

data can be mapping data with
integrated with AIS Integrating weather
Combining cell phone location
data to find the data with sales
customer reviews data can evaluate or
most efficient transaction data to
with inventory develop targeted
delivery routes, anticipate customer
turnover to assess advertising
reducing truck wear traffic patterns and
vendor and product campaigns or for
and tear by allow for better
effectiveness. marketing
reducing mileage service.
intelligence about
driven, reducing future products.
fuel costs, and
improving delivery
time.
 Data Velocity
• Data velocity refers to the
speed with which new data
points are generated.
• Data velocity is also related to
the terms big data and internet
of things.
• Big data refers to how high
data velocity can quickly
increase data volume.
• The higher the data velocity,
the faster data volume grows.
 Data Veracity
Data Veracity refers to the reliability, or the integrity of the data we
Theselect
reliability, or the integrity of the data we select for analysis.
for analysis.
Depends upon three things:
1.Depends
Whether theupon
datathree things:
will likely provide insights for the analysis
objective,
1. Whethereither
thebydata
itselfwill
or as a component
likely in an information
provide insights for the analysis objective,
either by itself ormodel, such as a netinincome
as a component calculation.
an information model, such as a
2. Hownet
accurate
income thecalculation.
data must be to generate useful insights for
2. How accurate the data must be to generate the useful
objective.
insights for the
3. How complete the data must be to generate useful insights
objective.
for the objective.
3. How complete the data must be to generate useful insights for the
objective.
 Data Value
Data Value refers to the benefits the data provides, given the
Theanalysis’
reliability,objective.
or the integrity of the data we select for analysis.
Depends upon three things:
1. Whether the data will likely provide insights for the analysis
Accountants’
objective, judgments
either by itself or asregarding
a component data value
in an depend on the
information
project’s objective: model, such as a net income calculation.
• Ifaccurate
2. How the objective
the data is to describe
must profits
be to generate or evaluate
useful insights forprofit trends,
then revenue and expense data are valuable the objective.
data.
3.• How complete
When the datathe
diagnosing must be to generate
causes useful insights
of decreasing operating cash flows,
for the objective.
data from the current asset and current liability accounts are
valuable.
Q: How does having more data around us
translate into value for a company?
 Value Creation
• Accountants' perspectives integrate knowledge across disciplines offering
The reliability,
a uniqueor the integrityadvantage.
competitive of the data we select for analysis.
• Thoughtful data analyses canDepends upon three
help improve things:and processes to
resources
1. Whether the data will likely provide insights for the analysis
increase operational competitiveness and achieve financial objectives.
objective, either by itself or as a component in an information
model, such as a net income calculation.
2. How accurate the data must be to generate useful insights for
the objective.
3.• How
Accounting
completefirms of allmust
the data sizesbeare quickly changing
to generate their business models to
useful insights
present themselves as expert advisorsfor who
thecreate value by performing
objective.
data analyses to improve governance, operations, and compliance
strategies for their clients.
Learning Objective 2

How does data analytics

affect business?

15
By the numbers:
▪ 85% of CEOs put a high value on Data Analytics.
▪ 86% of CEOs place data mining and analysis as the second-most
important strategic technology.
▪ Business analytics tops CEO’s list of priorities.

▪ Data analytics and technology could generate up to $2 trillion in

value per year.

16
Impact of Data Analytics
▪ Transformthe manner in which companies run their businesses in
the near future
▪ Value of data analytics to business
• e.g.
• Discover customer purchase pattern
• Investigate anomalies
• Forecast future possibilities
• Affect company’s internal process, improve productivity, utilization, and growth
Learning Objective 3

How does data analytics

affect accountants?

19
How does data analytics affect auditing?
▪ Data analytics enhances audit quality.
▪ Data analytics enables enhanced audits,
expanded services, and added value to clients.
▪ External auditors stay engaged beyond the
audit.

20
How does data analytics affect
management accounting?
▪ Data analytics enhances cost analysis.
▪ Data analytics enables better decision-making.
▪ Data analytics enables better forecasting, budgeting,
production, and sales.

21
 How does data analytics affect financial
reporting?
▪ Accountants make better estimates of collectability, write-downs, warranty claims,
etc.
• How much of the accounts receivable balance will ultimately be collected?
• What should the allowance for loan losses look like?
• Is any of the inventory obsolete? When will it be out of date?
• Has the goodwill been impaired due to the reduction in profitability from a recent merger? Will it regain
value in the near future?
• How should we value contingent liabilities like warranty claims or litigation? Do we have the right
amount?

▪ Managers better understand the business environment through social media.

▪ Analysts identify risks and opportunities through analysis of Internet searches.

22
How does data analytics affect tax?
▪ Companies develop sophisticated tax planning strategies.
▪ Managers understand tax consequences of international
transactions, investment, mergers and acquisitions.
▪ The organization understands tax tables and other tax data to aid
compliance.

23
Learning Objective 4

How does data analytics

make an IMPACT?

25
The IMPACT model
Identify the questions. Exhibit. The IMPACT Cycle

Master the data.

Perform the test plan.
Address and refine results.
Communicate insights.
Track outcomes.

26
IMPACT Model
Step 1: Identify the Questions
▪ Understand the business problems that need to be addressed.
• Are employees circumventing internal controls over payments?
• Are there any suspicious travel and entertainment expenses?
• How can we increase the amount of add-on sales of additional goods to our customers?
• Are our customers paying us in a timely manner?
• How can we predict the allowance for loan losses for our bank loans?
• How can we find transactions that are risky in terms of accounting issues?
• Who authorizes checks above $100,000?
• How can errors be identified?

27
IMPACT Model
Step 2: Master the Data
▪ Know what data are available and how they relate to the problem.
▪ Internal ERP systems.
▪ External networks and data warehouses.
▪ Data dictionaries.
▪ Extraction, transformation, and loading (ETL).
▪ Data validation and completeness.
▪ Data normalization.
▪ Data preparation and scrubbing.
28
IMPACT Model
Step 3: Perform the Test Plan
Select an appropriate model to find a target variable.
• Classification
◦ An attempt to assign each unit/individual in a population into a few categories.
• Regression
◦ A data approach used to predict a specific dependent variable value based on independent variable inputs
using a statistical model.
• Similarity matching
◦ An attempt to identify similar individuals based on data known about them.
• Clustering
◦ An attempt to divide individuals into groups in a useful or meaningful way.
• Co-occurrence grouping
◦ An attempt to discover association between individuals based on transactions involving them
◦ E.g., Amazon
29
IMPACT Model
Step 3: Perform the Test Plan
Select an appropriate model to find a target variable.
• Profiling
◦ An attempt to characterize the typical behavior of an individual group or population by generating
summary statistics about the data.
• Link prediction
◦ An attempt to predict connections between two data items.
◦ E.g. Facebook

30
IMPACT Model
Step 4: Address and Refine Results
▪ Identify issues with the analyses, possible issues, and refine
the model
▪ Ask further questions.
▪ Explore the data.
▪ Rerun analyses.

31
IMPACT Model
Step 5: Communicate Insights
▪ Communicate effectively using clear language and visualizations:
▪ Dashboards.
▪ Static reports.
▪ Summaries.

32
IMPACT Model
Step 6: Track Outcomes
▪ Follow up on the results of the analysis.
▪ How frequently should the analysis be performed?
▪ Have the analytics changed?
▪ What are the trends?

33
Class Exercise
Match each specific Data Analytics test to a specific test approach, as part of
performing test plan:
• Classification
• Regression
• Similarity Matching
• Clustering
• Co-occurrence Grouping
• Profiling
• Link Prediction
• Data Reduction
Class Exercise
Topic Answers

Predict which firms will go bankrupt and which firms will not go bankrupt.

Use stratified sampling to focus audit effort on transactions with greatest risk.

Work to understand normal behavior, to then be able identify abnormal

behavior (such as fraud).
Look for relationships between related parties that are not otherwise
disclosed.

Predict which new customers resemble the company’s best customers.

Predict the relationship between an investment in advertising expenditures

and subsequent operating income.

Segment all of the company’s customers into groups that will allow further
specific analysis.
The customers who buy product X will be most likely to be also interested in
product Y.
Learning Objective 5

What does data analytics

skills do accountants need?

38
Accountants need to be able to:
▪ Articulate business problems.
▪ Communicate with data scientists.
▪ Draw appropriate conclusions.
▪ Present results in an accessible manner.
▪ Develop an analytics mindset.

39
Q. What other skills might be useful in
performing Data Analytics?

40
Accounting
Knowledge
and Skills
Demand

41
 Summary
With data all around us, businesses and accountants are Different data approaches address different ways of testing
looking to Data Analytics to extract the value that the data the data: such as classification, regression, similarity
might possess. matching, clustering, co-occurrence grouping, profiling,
link prediction.
Data Analytics is changing the audit and the way that
accountants look for risk. Now, auditors can consider 100 Data analytic skills needed by analytic-minded accountants
percent of the transactions in their audit testing. It is also are specified and are consistent with the IMPACT cycle,
helpful in finding the anomalous or unusual transactions. including the following:
Data Analytics is also changing the way financial •Develop an analytics mindset.
accounting, managerial accounting, and taxes are done at •Data scrubbing and data preparation.
a company. •Data quality.
The IMPACT cycle is a means of doing Data Analytics that •Descriptive data analysis.
goes all the way from identifying the question, to •Data analysis through data manipulation.
mastering the data, to performing data analyses and •Define and address problems through statistical data
communicating results. It is recursive in nature, suggesting analysis.
that as questions are addressed, new important questions •Data visualization and data reporting.
may emerge that can be addressed in a similar way.

42
Thank you!
Contact me at:
[email protected]