A Framework for Testing Algorithmic Trading Strategies

Abstract

Algorithmic trading and artificial stock markets have generated huge interest not only among brokers and traders in the financial markets but also across various disciplines in the academia. The emergence of algorithmic trading has created a new environment where the classic way of trading requires new approaches. In order to understand the impact of such a trading process on the functioning of the market, new tools, theories and approaches need to be created. Thus artificial stock markets have emerged as simulation environments to test, understand and model the impact of algorithmic trading, where humans and software agents may compete on the same market. The purpose of this paper is to create a framework to test and analyse various trading strategies in a dedicated artificial environment.