English

Scila implements artificial intelligence for alert classification

Report this content

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 are in fact totally legitimate. Scila has always tried to minimize the risk for false positives when designing alert rules, and now Scila takes another huge step towards eliminating unnecessary alerts by introducing artificial intelligence for Scila Surveillance, Scila Compliance and Scila Regulator.

Together with Jens Wirén and Farhad Kimanos at the Department of Computer Science and Communication at The Royal Institute of Technology, Scila has developed a model for implementing classification of triggered alert by using advanced machine learning technology. By using this model the system can learn from the history of decisions made by human operators to try to predict a future decision, thereby reducing the workload for the Scila end-user analysts. Hedvig Kjellström, Associate Professor of Computer Science at The Royal Institute of Technology said, "We are very happy to contribute to the deployment of state-of-the-art machine learning methods in commercial systems, and to supervise students who participate in projects in industry."

Fredrik Lydén, CTO at Scila and the manager of this project is very pleased with the result. "This is a major step towards our ambition to minimize the number of false positives in our applications. We are continuously evaluating machine learning and artificial intelligence technology as a complement to traditional methods for detecting financial market anomalies. The current trend is that new regulatory and compliance requirements results in market data sets getting larger and larger, this makes it even more interesting to increase the use of machine learning."

"We are very pleased to co-operate with The Royal Institute of Technology. This is something that we aim to continue with going forward. Scila will always seek to improve its product portfolio, and co-operating with universities is an excellent way of gaining new input for development", commented Lars-Ivar Sellberg, Executive Chairman of Scila, and alumni of The Royal Institute of Technology.

For more information

Lars-Ivar Sellberg

Executive Chairman

Phone +46 733 47 87 10


Fredrik Lydén

Chief Technology Officer

Phone +46 73 707 30 11

About Scila AB 
Scila provides trading surveillance products built on many years of experience from both market surveillance and systems design. Scila Surveillance uses modern technology to give the customer a seamless route from detection of market abuse to presentable evidence. Scila delivers the future in modern market surveillance technology by offering trading venues, regulators and market participants the most competitive solution available. Scila’s sales and marketing partner Cinnober Financial Technology owns a minority stake in Scila AB and there is an exclusive sales agreement between the two companies. For additional information about Scila AB, please visit www.scila.se

Tags:

kth MiFID Artificial Intelligence Scila Scila Compliance surveillance technology Lars-Ivar Sellberg Trading Surveillance regulatory preassure market abuse Machine learning AI Fredrik Lydén Fredrik Lyden Scila AB Scila Regulator Hedvig Kjellström machine learning algorithms the Royal Institute of Technology Jens Wirén Jens Wiren Farhad Kimanos

Documents & Links

Quotes

We are very happy to contribute to the deployment of state-of-the-art machine learning methods in commercial systems, and to supervise students who participate in projects in industry.
Hedvig Kjellström, Associate Professor of Computer Science at The Royal Institute of Technology
This is a major step towards our ambition to minimize the number of false positives in our applications. We are continuously evaluating machine learning and artificial intelligence technology as a complement to traditional methods for detecting financial market anomalies. The current trend is that new regulatory and compliance requirements results in market data sets getting larger and larger, this makes it even more interesting to increase the use of machine learning.
Fredrik Lydén, CTO at Scila
We are very pleased to co-operate with The Royal Institute of Technology. This is something that we aim to continue with going forward. Scila will always seek to improve its product portfolio, and co-operating with universities is an excellent way of gaining new input for development
Lars-Ivar Sellberg, Executive Chairman of Scila