We find that actual trading costs are less than a tenth as large as, and therefore the potential scale of these strategies is more than an order of magnitude larger than, previous studies suggest. Using nearly a trillion dollars of live trading data from a large institutional money manager across 19 developed equity markets over the period 1998 to 2011, we measure the real-world transactions costs and price impact function facing an arbitrageur and apply them to size, value, momentum, and short-term reversal strategies. The agent’s simulated and live trading results lead us to believe our infrastructure can be of practical interest to the traditional trading community. This infrastructure was used to develop an agent capable of trading the USD/JPY currency pair with a 6 hours timeframe.
The “A Priori Knowledge Module”, implemented using a Rule-Based Expert System, enables the agents to incorporate non-experiential knowledge in their trading decisions.
The “A Posteriori Knowledge Module”, implemented using a Case-Based Reasoning System, enables the agents to learn from empirical experience and is responsible for suggesting how much to invest in each trade. The “Intuition Module”, implemented using an Ensemble Model, is responsible for performing pattern recognition and predicting the direction of the exchange rate. This infrastructure is composed of three modules. In this paper we describe an infrastructure for implementing hybrid intelligent agents with the ability to trade in the Forex Market without requiring human supervision.
0 kommentar(er)
