Gated Bayesian networks for algorithmic trading

Abstract

This paper introduces a new probabilistic graphical model called gated Bayesian network (GBN). This model evolved from the need to represent processes that include several distinct phases. In essence, a GBN is a model that combines several Bayesian networks (BNs) in such a manner that they may be active or inactive during queries to the model. We use objects called gates to combine BNs, and to activate and deactivate them when predefined logical statements are satisfied. In this paper we also present an algorithm for semi-automatic learning of GBNs. We use the algorithm to learn GBNs that output buy and sell decisions for use in algorithmic trading systems. We show how the learnt GBNs can substantially lower risk towards invested capital, while they at the same time generate similar or better rewards, compared to the benchmark investment strategy buy-and-hold . We also explore some differences and similarities between GBNs and other related formalisms. • We present a new probabilistic graphical model which we call gated Bayesian networks. • A semi-automatic algorithm is presented that can learn a gated Bayesian network. • Gated Bayesian networks are applied to the domain of algorithmic trading. • We show that gated Bayesian networks can improve results over a standard benchmark. • We compare gated Bayesian networks to other common models and formalisms.