Investment Portfolio Management
Over the past few years, we have witnessed profound changes in the marketplace with participants increasingly adopting quantitative investing techniques. These include consumption of increasing amounts and differentiated types of data, and adoption of new methods of analysis such as those based on machine learning. In portfolio management, we can help banks to leverage machine learning tools to identify new signals on price movements and to make more effective use of the vast amount of available data and market research than with current models. We work on the same principles as existing analytical techniques used in systematic investing. The key task we address is the stock selection problem i.e. identifying signals from data on which predictions relating to price level or volatility can be made, over various time horizons, to generate higher and uncorrelated returns.
Seeking to increase productivity and simultaneously reduce costs and risks, while complying with regulations, banks can employ machine learning for Anti-Money Laundering (AML). Investigating suspicious transactions is time consuming and often suffers from a high rate of false positives. We offer design and development of machine learning systems for identification of suspicious transactions that warrant further attention, allowing AML experts to focus on higher risk transactions. Machine learning is used to identify complex patterns from transactions data, client profiles, and a variety of unstructured data, and thus uncovering non-linear relationships among different attributes and entities, and detecting potentially complicated behavior patterns of money laundering not directly observable through conventional methods.