Rules-Based Integration of News-Trading Algorithms

Abstract

We propose a rules-based approach to optimize news-trading systems, where each event is screened by a limited number of relevant text and data-analysis algorithms. Those are selected automatically from a set of executable components, and are integrated in iterative workflows based on knowledge or rules database of market and event conditions. Events may also be chained together to detect emerging patterns through time, and to provide performance benchmarks among comparable scenarios and strategies. We review recent advances in news trading, and present the architecture of a next-generation system for rules-based integration of algorithms that could provide more effective execution and fund management in the context of high-frequency trading (HFT).