Trading alternative assets is complicated business. In contrast to equities trading, there is a lengthy and multi-tiered compliance workflow to ensure clearance of trades. The iteration between "what-if" trade scenarios and compliance scoring is one of connected data, as a trader's strategy can be represented as a set of edges in a graph structure where nodes represent instruments in a portfolio. We can then deploy machine learning algorithms to assist a compliance officer in scoring the strategy, dramatically increasing efficiency. Furthermore, we can use modern graphML techniques to recommend best possible actions to a trader in real time, increasing her efficiency as well. Once the technical and algorithmic complexity has been tackled, the challenge of conveying this complex information to constituents in a way that is timely, comprehensible and actionable still remains.
YOU MAY ALSO LIKE:
Trading Alternative Assets using Connected Data
Chris LaCava. Chris has spent the past two decades defining, designing and building software for a variety of industry verticals. He has experience as a usability engineer, interaction designer, front-end developer as well as product manager for both consulting and product-oriented organisations. Chris earned his B.A. in Anthropology and Behavioural Science from Hampshire College. Prior to joining the Expero team, Chris worked to bring healthcare-related software solutions to market for Visible Health as VP of Product.
Graham Ganssle, PhD. Dr. G is a specialist in the field of deep learning. His education focused on digital signal processing and optimisation of recursively dependent nonlinear physical systems. His expertise is currently focused on autonomous generative systems and modern methodologies for time series analysis and forecasting. Graham and his team architect and build machine learning systems to leverage the huge amount of data collected in many domains, including the trading business.