Abstract In recent times, incremental and online machine learning receive more and more attention especially in the context of learning from real-time data streams, in contrast with a traditional assumption of complete data availability. Although a variety of different methods are available, it often remains unclear which of them is…

Global Companies Should Focus on Behavior, rather than Simply Complying with the Law — Abstract Widespread use of Artificial intelligence (AI) technologies in financial institutions and financial crime risk management systems have encouraged debate around the ethical challenges and risks AI-based technology pose. …

Content Introduction What is Feature Selection What Makes Some Feature Better Than Others Feature Selection by Label Information Supervised Feature Selection Unsupervised Feature Selection Feature Selection — Data Perspective Characteristics of Feature Selection Algorithm Feature Stability Feature Representation in Financial Crime Reference Introduction As a dimensionality reduction technique, feature selection aims to…

While AI-based systems were primarily used to gain operational efficiencies in financial crime, model fairness and data bias occur when a…

Fraud Prevention: Exploration-Exploitation Tradeoff in AI-based Systems

Nefarious industries rely on sophisticated money laundering schemes to operate. Money laundering, known as the process that transforms the proceeds of crime into clean legitimate assets, is a common phenomenon occurring all over the world. Illegally obtained money is typically ‘cleaned’ thanks to transfers that involve banks or legitimate businesses…

Support Vector Machines (SVMs) is a popular tool for learning with large amounts of high dimensional data. However, it may sometimes be preferable to learn incrementally from previous SVM results, as computing an SVM is very costly in terms of time and memory consumption or because the SVM may be…