Scribd
Upload
74 views

Fraud Analytics Course Outline

This document outlines a module on fraud analytics. It will examine prominent financial reporting frauds using case studies to understand when, how, and why they occurred and the roles of management, boards of directors, and auditors. Students will learn how to use data analytics and technologies like Python, R, and Power BI to improve audit effectiveness. The module aims to help students understand different fraud schemes and detection methods, use software to automate procedures, and develop critical thinking and communication skills. Students will be assessed through semester assignments, presentations, tests, and an examination. The module content will cover topics like data sources and characteristics, data cleaning, introduction to fraud, using models to analyze financial statements for anomalies, and machine learning techniques in fraud

Uploaded by

Tarisai Guvheya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
74 views

Fraud Analytics Course Outline

This document outlines a module on fraud analytics. It will examine prominent financial reporting frauds using case studies to understand when, how, and why they occurred and the roles of management, boards of directors, and auditors. Students will learn how to use data analytics and technologies like Python, R, and Power BI to improve audit effectiveness. The module aims to help students understand different fraud schemes and detection methods, use software to automate procedures, and develop critical thinking and communication skills. Students will be assessed through semester assignments, presentations, tests, and an examination. The module content will cover topics like data sources and characteristics, data cleaning, introduction to fraud, using models to analyze financial statements for anomalies, and machine learning techniques in fraud

Uploaded by

Tarisai Guvheya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

UNIVERSITY OF ZIMBABWE

FACULTY OF BUSINESS MANAGEMENT SCIENCES & ECONOMICS

DEPARTMENT OF BUSINESS ENTERPRISE

MODULE OUTLINE FOR FRAUD ANALYTICS

Module Convener: Mr T Tazvishaya– Msc in Big Data Analytics (CUT); M .Acc (UZ); B.Acc
Honours (UZ), CTA (Level 2), Substantive Laws (Honours) student, UZ
Contact details: 0773 610 198;
Email: [email protected]
Office 143 1st Floor Business Enterprise Management Dept

1. Module description
We will examine prominent financial reporting frauds using the case study method to understand
when, how and why they occurred, as well as the roles that management, the Board of Directors and
auditors played. While examining the lessons learned from these situations, we will explore what
management, the Board of Directors and auditors might have done differently, including how the
use of data analytics could have assisted in the prevention or earlier detection. The course will also
focus on the use of data analytics in auditing using a competency framework that fosters an analytics
mindset. Hands-on case studies using current technologies (e.g., Python, R, STATA, Power BI, SQL
Query) to learn how data visualization and analysis are used to improve audit effectiveness in
today’s accounting profession
NB: Lecture material is only intended to guide students. Therefore students are required to
do a large amount of self-study. Lecture notes as well as articles on different principles will
be provided to students.
2. Learning outcomes
From the course, students are expected to:
• Understand the different fraud schemes and their prevention and detection methods
• Explore the useful of technologies (e.g., Tableau or IDEA) in fraud
examination/investigation
• Use software to automate detection and identification procedures
• Develop effective critical thinking and analytical skills
• Demonstrate effective verbal and written communication skills • Perform research to
resolve accounting questions
• Work effectively in pairs or groups
• Address the ethical considerations surrounding fraud
3. Method of assessment
 Semester assessment – 50% (This will include presentations, assignments and tests
 Examination – 50%
4. MODULE CONTENT
4.1 Introduction

 What is data and its types (Qualitative, Quantitative, Cross sectional, Time series,
Panel, Discrete, Categorical etc)
 Data Measurement and recording scales (Ordinal, Nominal, Ratio, Scale)
 Data Sources (Secondary and Primary, Internal, External, Websites, Databases)
 Explain today’s data characteristics (Vs of today’s data e.g Volume, Variety,
Velocity, Value, Veracity etc;
 Data collection methods and sampling techniques (ODK, Kobo tool box, Google
forms, Survey Monkeys; Probability sampling techniques.
 Any other areas that deals with data and its formats
 N.B From here going forward all forms of data shall be used which include Cross
Sectional, Time Series Modelling, Panel Data Modelling, Social media, Textual
Analytics
 Getting started in collecting data for Fraud Analytics (SQL, python, R)

4.2 Data cleaning and pre-processing


 Exploratory Data Analysis (EDA)
o Checking data for missing values and fixing the missing values
o Checking outliers and fixing the outliers
o Checking for duplicates and fixing the data
o Data recording, relabel, merging data sets, separating values in the same
columns etc
o Creating new variables, collapsing variables
o Dropping inconsistent data, variables
o Variable selection using AGNES & DIANA method
o Data dimension reduction techniques (Clustering, Factor Analysis,
Discriminant Analysis, Random Forests, and Nearest Neighbourhood
Analysis).
o Appending, concatenation, merging of variables and data sets
o Randomisation of data (Checking if data follows a random variables)
o Checking for normality test (skewness, kurtosis, JB, Shapiro Wilk)
o Fixing data that is not normal (log methods, sample size, qrange)
o Checking data for collinearity problems (Spearman, Pearson, Kendall)
o Dealing and fixing
o Data Visualisation (scatter plots, histograms, etc).
o VIF

4.3 Introduction to Fraud Analytics


o What is Fraud? Seriousness of fraud problem.
o Criminal and Civil Prosecution of Fraud and Fraud-related (Class discussion)
o Why does it happen?
o Who is responsible for preventing and detecting it?
o Why people commit fraud? Good intentions vs Bad Outcomes
 How might we use computers and data analysis techniques to prevent
and detect fraud?
 Examples of Fraud
 Anomaly detection using Benford’s Law in Fraud Analytics
 Fighting fraud, preventing fraud.
 Dealing with data in Fraud (refer to 4.1 & 4.2)
 Computer analysis and visualization techniques.
 Sorting, indexing, summarizing, and stratifying.
 Duplicate detection.
 Joining data tables.
 Pivot tables and cross tabulation.
 Dimensionality reduction (Clustering, PCA, Factor Analysis)

4.4 Financial Statements Fraud Analytics (Using both the Model and the
Lev-Thiagarajan Model to analyze financial statements for possible anomalies in the
information).

 Journal Entry Data Analytics


 Financial statements Fraud analytics
 Earnings Management (The Beneish M-Score Model)
 Revenue and inventory frauds
 Liability, Asset, inadequate disclosure frauds
 Going concern (Health checking) using Piotroski F-Score, Z-Score Analysis,
CRO and cash flow analysis, Sloan's Accruals, Dechow-Dichev Accrual Quality,
Jones Non-discretionary Accruals
4.5 Machine Learning in Fraud Analytics
 Linear Regression
 Association rule learning
 Classification
 Decision tree learning and logistic regression
 Confusion Matrix and Cross Validation

You might also like