One source of trust for physical trading systems is their physical assets and simply their presence. A similar baseline does not exist for electronic trading systems, but one way in which it may be possible to create that initial trust is through the abstract notion of an institution, defined in terms of norms [19] and the scenes within which (software) agents may play roles in different tradin...

We present a methodology to discover how often the price deviates from established levels without sound reason. We look at the distribution of these so called “rare events” during the trading day and analyze the speed of the price bouncing back to the levels established before the rare events. We provide methods to calibrate trading rules based on the detection of these events and we exemplify ...

A lgorithmic trading of securities has become a staple of modern approaches to financial investment. In this project, I attempt to obtain an effective strategy for trading a collection of 27 financial futures based solely on their past trading data. All of the strategies that I consider are based on predictions of the future price and volatility of the various securities under consideration, an...

Abstract. Gated Bayesian networks (GBNs) are a recently introduced extension of Bayesian networks that aims to model dynamical systems consisting of several distinct phases. In this paper, we 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 using the learnt GBNs can...

The availability of data on digital traces is growing to unprecedented sizes, but inferring actionable knowledge from large-scale data is far from being trivial. This is especially important for computational finance, where digital traces of human behaviour offer a great potential to drive trading strategies. We contribute to this by providing a consistent approach that integrates various datas...

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 ...

The availability of data on digital traces is growing to unprecedented sizes, but inferring actionable knowledge from large-scale data is far from being trivial. This is especially important for computational finance, where digital traces of human behaviour offer a great potential to drive trading strategies. We contribute to this by providing a consistent approach that integrates various datas...

This paper examines the relative liquidity and rate of price discovery on floorbased versus screen-based trading systems in the Japanese Yen, British Pound, and Euro foreign exchange futures markets traded on the Chicago Mercantile Exchange (CME). Intra-day data from January 2, 2003 through March 5, 2004 are used in our analysis. We find that liquidity, measured by bid-ask spreads, is tighter i...