Data Analytics for Fraud Detection

This course bridges data science and financial technology by introducing computational methods to combat financial crimes, such as money laundering, fraud, and the financing of illicit activities. Students will explore how data science techniques can be applied to transactional and customer data to identify anomalies and suspicious behavior. The course integrates data pre-processing, machine learning algorithms, and network analysis methods tailored towards financial crime detection. In addition, it examines regulatory frameworks, ethical considerations, and potential future developments in the field. Graduates will develop the skills to analyze and present in-class complex real-world cases, to design algorithms for anomaly detection, and to navigate the ethical and regulatory challenges in the prevention of financial crime.

• Analyze and model financial transactions to detect anomalies indicative of fraudulent activities.
• Apply supervised and unsupervised machine learning algorithms to financial datasets.
• Critically evaluate the ethical and regulatory implications of data-driven financial crime prevention.
• Analyze and present in class real-world cases of financial crime.

In presence

Lectures and presentations.

• Student assignments and presentations: 40%
• Final oral exam: 60%