Traditional black-box based compliance has had limited success in detecting fraud because its focus is too restrictive. While individual transactional analysis is important contextual analysis needs to survey a wider spectrum. It’s now accepted that detection is not just about individual systems and trades, it’s not just about fixed limits and parameters, it’s not just about siloed reports and audit trails – it’s about all the interactions, dependencies, changes, communications, patterns and behaviours across the trade lifecycle and the organization, that standalone alerts and static rules simply don’t catch. While many solution focus in specific aspects of data analysis (e.g. trade, voice, email), until now there has been no solution that can give true multi-factorial analysis across them all. Kx for Surveillance is that solution.
- Behavioral analytics libraries including, but not limited to, Market Abuse and Insider Trading, AML, eComms and Employee fraud
- Multifactorial modelling over hundreds of risk factors to build risk profiles and behavioral anomalies
- Incorporation of all major Machine Learning libraries for supervised and unsupervised learning
- Rich contextual investigation dashboards and ad-hoc data mining
- Extensive workflow and case management
- Extensible and open platform for data modelling and investigation
By aggregating data across multiple sources and disparate formats it enables contextual analysis, workflow, audit and transparency that not only ensures regulatory compliance, but also gives massive operational savings through fewer false positives and efficiency in ensuring risk controls are met.
Kx for Surveillance - Combining Transactional and Behavioral AnalysisKx offers solutions for both transactional and eComms surveillance that can be deployed separately or in combination on the same platform to instantly detect behavioral changes and known violations like layering, spoofing or marking the close.
The advantages of amalgamating transactional and eComms data in a single unified platform include the ability to investigate and interrogate all sets of data in one place, greatly enhancing the detection and investigation of unauthorized trading activity.
Click on the link below to read about using behaviour analytics to reduce financial crime.
Machine Learning and eComms SurveillanceMachine Learning techniques are changing the surveillance methodology from being lag-indicator driven to lead-indicator driven where, like cyber security, the focus is detection of intent and threat avoidance rather than after-the-event conviction when the financial and reputational damage has already been done. Machine Learning techniques like Natural Language Processing (NLP) can also be used in the investigation phases to parse documents, texts and other communications to uncover suspicious activity and assist in the prosecution phase by providing corroborating evidence.
Click on the link below to read how Kx uses Machine Learning in its eComms surveillance solution.
Backtesting and Market ReplayRegulators and bank compliance departments are dealing with ever increasing volumes of complex trading data which makes identifying anomalies difficult. With Kx it is possible to backtest many years of trading data to efficiently calibrate scenarios and identify irregular behavior, minimizing false positives.
View Order Book Replay
Flexible AlertsThe CEP engine within Kx for Surveillance enables instant detection of trends or patterns that may indicate market abuse, erroneous trading or malfunctioning algorithms. Flexible configuration of alert parameters and thresholds enables more accurate detection rates and comprehensive, easy-to-use market replay functionality further improves the efficiency of investigations. Some customers have reported the time taken to analyze potential breaches being reduced from months to minutes.
Multi Asset and Multi MarketThe Kx platform captures and consolidates all trading data (rates, trades, orders, news) for FX, credit, rates, commodities, equities and listed derivatives. Built on technology chosen by top global banks for their high frequency trading systems, Kx for Surveillance was designed in collaboration with market participants to give analysts and business users a comprehensive view of relevant market activity.
The basis for Kx Technology is a unique integrated platform which includes a high-performance historical time-series columnar database called kdb+, an in-memory compute engine, and a real-time streaming processor all unified with an expressive query and programming language called q.
Designed from the start for extreme scale, and running on industry standard servers, the kdb+ database has been proven to solve complex problems faster than any of its competitors.LEARN MORE