BEHAVIORAL ANALYTICS LIBRARIES
The ability to create windowed views of larger datasets is baked into the programming language q. Our powerful window-join functionality enables users to contextualise easily between data tables over entirely customisable windows.
Choose from hundreds of risk factors to build risk profiles and behavioral anomalies.
INCORPORATION OF MACHINE LEARNING
Apply all major ML libraries for supervised and unsupervised learning.
RICH CONTEXTUAL INVESTIGATION
Bring to life investigations with dashboards and ad-hoc data mining.
WORKFLOW AND EXTENSIBLE OPEN PLATFORM
Extensive case management with an open platform for data modelling and investigation.
Machine 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.
KX for Surveillance – Combining Transactional and Behavioral Analysis
KX 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.
Backtesting and Market Replay
Regulators 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.
The 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 Market
The 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.