Fraud Detection in financial institutions: Prevention and management
The variations are so numerous and the examples of training so rare, that it is not possible to know what a fraudulent activity or an incident looks like.
- Overview of problems & types of supervised and unsupervised learning for the detection of anomalies
- Main Anomaly Detection Learning Models and Algorithms
- Practice on datasets with scikit-learn (http://scikit-learn.org/) under Python on case studies from the banking sector.
- Build a fraud detection model in banking transactions
- Implementation of an empirical study using supervised learning algorithms for churn prediction and for automatic bank credit approval.
- Detect anomalies by learning what normal activity looks like (using a history of supposedly non-fraudulent transactions) and identifying anything very different.
- Supervised and other unsupervised approaches to fraud detection
- Experimentation with solutions to respond to various problems related to the detection of anomalies with the Python language, in the banking and financial fields.
Reservation ends in
Join us and be part of the great ICT event in Africa alongside decision makers and prime contractors from Tunisia, Africa and elsewhere. Come Share your experiences and participate in exchanges to contribute to the development of South-South collaboration links.
Tel: 216 71 975 035 / 71 975 054
Fax: +216 71 975 352
Adress: Kram Exhibition Center