Scila implements artificial intelligence for alert classification

Scila, together with The Royal Institute of Technology, has been working with machine learning algorithms for alert classification in Scila's trading surveillance software. This has been done through a Bachelor Thesis at the Department of Computer Science and Communication at The Royal Institute of Technology. The authors are Mr Jens Wirén and Mr Farhad Kimanos.One of the major challenges when you design an alert rule for a trading surveillance system is to keep the number of false positives to a minimum, i.e. trading patterns that look like market abuse and therefore trigger an alert, but