About this programme

This course builds advanced capabilities in the use of artificial intelligence and data analytics to detect, prevent, and investigate fraud. It focuses on applying AI-driven models, machine learning techniques, and advanced analytical tools to identify fraud patterns, anomalies, and emerging risks across financial and operational data. The course supports data-driven fraud risk management, stronger internal controls, and enhanced investigative effectiveness in complex organizational environments.

Duration

5 Days

Who Should Attend:

Fraud risk and investigation officers
Internal and external auditors
Risk and compliance professionals
Data analysts and finance professionals
IT, cybersecurity, and forensic specialists

Learning outcomes

What you'll walk away with

By the end of the course, participants will be able to:

Understand AI and machine learning concepts relevant to fraud analytics
Apply advanced analytics techniques to detect fraud patterns and anomalies
Use AI-driven tools to enhance fraud prevention and investigation
Interpret analytical results for decision-making and reporting
Strengthen organizational fraud risk management frameworks

Course modules

What we cover, module by module

Module 1: Fraud Risk & Advanced Analytics Overview

Fraud typologies and risk factors
Evolution from traditional fraud detection to AI-driven analytics
Data requirements for fraud analytics
Case Study: Undetected fraud due to weak analytical capabilities
Practical: Mapping fraud risks to available data sources

Module 2: Data Preparation & Feature Engineering for Fraud Detection

Data quality, cleansing, and integration
Feature engineering for fraud indicators
Structured and unstructured data in fraud analytics
Case Study: Poor data quality and false positives
Practical: Preparing datasets for fraud analysis

Module 3: Machine Learning Techniques for Fraud Detection

Supervised vs unsupervised learning
Classification, clustering, and anomaly detection models
Model training and validation
Case Study: Machine learning models uncovering transaction fraud
Practical: Designing a fraud detection model

Module 4: AI-Driven Fraud Monitoring & Investigation

Real-time fraud monitoring systems
Alert management and case prioritization
Linking analytics to investigations
Case Study: AI-enabled fraud investigation workflow
Practical: Interpreting model outputs and alerts

Module 5: Ethics, Governance & Future Trends in Fraud Analytics

Model risk management and explainable AI
Data privacy and ethical considerations
Emerging trends in AI-driven fraud detection
Case Study: Regulatory concerns around AI use in fraud detection
Practical: Developing an AI fraud analytics governance framework

Impact

Where the change lands

Personal Impact:

Advanced analytical and AI skills for fraud detection
Improved investigative judgment and decision-making
Increased confidence in using AI-driven tools

Organizational Impact:

Improved fraud detection and prevention capabilities
Reduced financial losses and reputational risk
Stronger governance, compliance, and internal controls

Dates and locations

Upcoming intakes

Every intake is limited to a small cohort. Booking closes when a date fills or three weeks before the start, whichever comes first.

Full calendar

City	Starts	Ends	Delivery	Book
NakuruNext	20 Jul 2026	24 Jul 2026	In-Person	Book
Kigali	20 Jul 2026	24 Jul 2026	In-Person	Book
Accra	20 Jul 2026	24 Jul 2026	In-Person	Book
Kisumu	27 Jul 2026	31 Jul 2026	In-Person	Book
Johannesburg	27 Jul 2026	31 Jul 2026	In-Person	Book
Dakar	27 Jul 2026	31 Jul 2026	In-Person	Book