Evolving Dynamic Trade Execution Strategies Using Grammatical Evolution

Abstract

Abstract. Although there is a plentiful literature on the use of evolutionary methodologies for the trading of financial assets, little attention has been paid to potential use of these methods for efficient trade execution. Trade execution is concerned with the actual mechanics of buying or selling the desired amount of a financial instrument of interest. Grammatical Evolution (GE) is an evolutionary automatic programming methodology which can be used to evolve rule sets. In this paper we use a GE algorithm to discover dynamic, efficient, trade execution strategies which adapt to changing market conditions. The strategies are tested in an artificial limit order market. GE was found to be able to evolve quality trade execution strategies which are highly competitive with two benchmark trade execution strategies.

Applications of genetic programming to finance and economics: past, present, future

“…A novel approach was taken by [32,33] where grammatical evolution (GE) was used to evolve a dynamic trade execution strategy, with the resulting rule adapting to changing market conditions. Based on the finance literature analysing the relationship between order placement and the information content of limit order books, six order book metrics were selected as potential inputs for an execution strategy.…”

Revisiting Agent-Based Models of Algorithmic Trading Strategies

“…Noise agents (zero intelligence) Many researchers choose to use zero intelligence agents in their financial market simulations, for example in the models presented in [12,13,18,28]. There is a strong empirical evidence backing up such a widespread use of noise agents - [18] has shown that noise agents with parameters derived from empirical data can explain up to 96% of the variance of spreads and 76% of the diffusion rates.…”

“…There exist a number of noise agent variations. Relatively complicated strategies for noise traders are used in [12][13][14]. In these papers, the agents can submit Buy and Sell orders with equal probabilities, and can submit Limit and Market orders, or can cancel existing an limit order if it was not yet executed.…”

“…The size of the market and limit orders follow power law distributions, with different parameters. The corresponding set of parameters suggested by [13] is presented in Table 1.…”

Evolving efficient limit order strategy using Grammatical Evolution

“…In our previous work [6], GE has been used to evolve quality trade execution strategies which determine appropriate time to change limit orders to market orders. GE evolved strategies have been proved to outperform two benchmark strategies: simple market order strategy and simple limit order strategy.…”