Accounting Information Systems

Fifteenth Edition

Chapter 5
Introduction to Data Analytics in
Accounting
Learning Objectives
• Explain what makes a good question and evaluate
questions relative to the SMART framework.
• Describe the extract, transform, and load (ETL) process
and key components of each step of the process.
• Explain the differences between descriptive, diagnostic,
predictive, and prescriptive analytics. Understand the
situations for which each type of analytic is appropriate.
• List the principles that lead to high-quality data
visualizations.
• Describe how automation interacts with the analytics
mindset and when data analytics is not the right tool for
making a decision.
The Four V’s of Big Data
• Big data is the term companies use to describe the
massive amounts of data they now capture, store, and
analyze.
– Data volume refers to the amount of data created and
stored by an organization.
– Data velocity refers to the pace at which data is
created and stored.
– Data variety refers to the different forms data can take.
– Data veracity refers to the quality or trustworthiness of
data.
An Analytics Mindset
• A mindset is a mental attitude, a way of thinking, or a
frame of mind.
– An analytics mindset is a way of thinking that centers
on the correct use of data and analysis for decision
making.
• According to EY, an analytics mindset is the ability to
– Ask the right questions.
– Extract, transform, and load relevant data.
– Apply appropriate data analytic techniques.
– Interpret and share the results with stakeholders.
Ask the Right Questions
• A good data analytic question is
– Specific: needs to be direct and focused to produce a
meaningful answer.
– Measurable: must be amenable to data analysis and
thus the inputs to answering the question must be
measurable with data.
– Achievable: should be able to be answered and the
answer should cause a decision maker to take an
action.
– Relevant: should relate to the objectives of the
organization or the situation under consideration.
– Timely: must have a defined time horizon for
answering.
Extract, Transform, and Load
Relevant Data
• The process of extracting, transforming, and loading data
is often abbreviated as the ETL process.
– The ETL process is often the most time-consuming part
of the analytics mindset process.
– Repetitive ETL processes can be fully automated so
the extracting, transforming, and loading data is done
entirely by a computer program in what appears to be a
single, unified step.
Extracting Data
• There are three steps in the data extraction process
– Understand data needs and the data available.
– Perform the data extraction.
– Verify the data extraction quality and document what
you have done.
Figure 5.1 Three Alternative Structures:
Data Warehouse, Data Mart, and Data Lake
Table 5.1 Examples of Delimiters and Text Qualifiers
Transforming Data
• There are four steps in the data transformation process
– Understand the data and the desired outcome.
– Standardize, structure, and clean the data.
– Validate data quality and verify data meets data
requirements.
– Document the transformation process.
Loading Data
• There are a few important considerations when loading
data.
– The transformed data must be stored in a format and
structure acceptable to the receiving software.
– Programs may treat some data formats differently than
expected. It is important to understand how the new
program will interpret data formats.
• Once the data is successfully loaded into the new
program, it is important to update or create a new data
dictionary.
Apply Appropriate Data Analytic
Techniques
• There are four categories of data analytics
– Descriptive analytics are information that results from the
examination of data to understand the past answers to the
question “what happened?”
– Diagnostic analytics build on descriptive analytics and try
to answer the question “why did this happen?”
– Predictive analytics are information that results from
analyses that focus on predicting the future—they address
the question “what might happen in the future?”
– Prescriptive analytics are Information that results from
analyses to provide a recommendation of what should
happen—answers the question “what should be done?”
Figure 5.2 Ernst & Young Foundation
Recommended Data Analytics Skills
Interpreting Results
• Interpreting results can be complicated.
• One common way people interpret results incorrectly
relates to correlation and causation.
– Correlation tells if two things happen at the same time.
– Causation tells that the occurrence of one thing will
cause the occurrence of a second thing.
• A second common misinterpretation of results is noted in
psychology research.
– Psychology research provides evidence of systematic
biases in the way people interpret results.
Sharing Results
• Data storytelling is the process of translating often
complex data analyses into more easy to understand
terms to enable better decision making.
• To tell a successful data story, you will need to
– remember the question that initiated the analytics
process.
– consider the audience.
– use data visualizations.
Data Visualization
• Data visualization is the use of a graphical representation
of data to convey meaning.
• Good principles of visualization design include:
– Choosing the right type of visualization.
– Simplifying the presentation of data.
– Emphasizing what is important.
– Representing the data ethically.
Automation
• Automation is the application of machines to
automatically perform a task once performed by humans.
• Robotic process automation (RPA) is computer software
that can be programmed to automatically perform tasks
across applications just as human workers do.
– Companies are using RPA and other automation
software to automate tasks within their analytics
processes.
– RPA is one tool that can be used to automate ETL
tasks.
Data Analytics is not Always the
Right Tool
• Data analytics is not always the correct tool to reach the
best outcome.
– Reliable data does not exist for aspects of many
questions.
– Human judgment or intuition may be able to account
for sentiment factors that cannot be reliably measured.
• Data can help us make better decisions, but we need to
remember the importance of
– intuition, expertise, ethics, and other sources of
knowledge that are not easy to quantify but that can
have a significant impact on performance.
Key Terms (1 of 2)
• Big data • Dark data
• Data volume • Data swamps
• Data velocity • Metadata
• Data variety • Data owner
• Data veracity • Flat file
• Mindset • Delimiter
• Analytics mindset • Text qualifier
• E T L process • Descriptive analytics
• Structured data • Diagnostic analytics
• Unstructured data • Predictive analytics
• Semi-structured data • Prescriptive analytics
• Data marts • Data storytelling
• Data lake • Data visualization
Key Terms (2 of 2)
• Data dashboard
• Automation
• Robotic process automation (R P A)
• Bot
Copyright

This work is protected by United States copyright laws and

is provided solely for the use of instructors in teaching their
courses and assessing student learning. Dissemination or
sale of any part of this work (including on the World Wide
Web) will destroy the integrity of the work and is not
permitted. The work and materials from it should never be
made available to students except by instructors using the
accompanying text in their classes. All recipients of this
work are expected to abide by these restrictions and to
honor the intended pedagogical purposes and the needs of
other instructors who rely on these materials.