An Application of Multi-objective particle swarm optimization to end-of-day Historical Stock Trading

Antonio Briza

(MS Graduated: 2nd Sem 2007-2008)

Abstract

Stock traders consider several factors or objectives in making decisions. Moreover, they differ in the importance they attach to each of these objectives. This requires a tool that can provide an optimal tradeoff among different objectives, a problem aptly solved by a multi objective optimization (MOO) system.

MOO has been successfully applied to intraday stock trading in an artificial stock exchange. While this proves that MOO can be used as a tool for intraday live trading, it also makes the development of a MOO tool for historical end-of-day market data necessary in order to cater to longer-term traders. This is the problem we would like to address. This paper aims to investigate the application of MOO to end-of-day historical stock trading. Concretely, we present a stock trading system that uses multi objective particle swarm optimization (MOPSO) of financial technical indicators. Using end-of-day market data, the system optimizes the weights of several technical indicators over two objective functions, namely, percent profit and Sharpe ratio.

The performance of the system was compared to the performance of the technical indicators and the market itself. The results show that the system performed well on both training and out-of-sample data. In terms of percent profit, the system was able to beat most, if not all, of the indicators under study, and, in some instances, even beat the market itself. In terms of Sharpe ratio, the system consistently performed significantly better than all the technical indicators. The system provided a diversity of solutions for t he two objective functions and is found to be robust and fast. These results show the potential of the system as a tool for making stock trading decisions.