Abstract: We use a genetic algorithm to learn technical trading rules for the S&P 500 index using daily prices from 1928 to 1995. After transaction costs, the rules do not earn consistent excess returns over a simple buy-and-hold strategy in the out-of-sample test periods. The rules are able to identify periods to be in the index when daily returns are positive and volatility is low and out when the reverse is true. These latter results can largely be explained by low-order serial correlation in stock index returns.

Abstract: One of the major challenges in an information-rich financial market is how effectively to derive an optimum investment solution among vast amounts of available information. The most efficacious combination of factors or information signals can be found by evaluating millions of possibilities, which is a task well beyond the scope of manual efforts. Given the limitations of the manual approach, factor combinations are typically linear. However, the linear combination of factors might be too simple to reflect market complexities and thus fully capture the predictive power of the factors. A genetic programming process can easily explore both linear and non-linear formulae. In addition, the ease of evaluation facilitates the consideration of broader factor candidates for a stock selection model. Based upon State Street Global Advisors (SSgA)’s previous research on using genetic programming techniques to develop quantitative investment strategies, we extend our application to develop stock selection models in a large investable stock universe, the S&P 500 index. Two different fitness functions are designed to derive GP models that accommodate different investment objectives. First, we demonstrate that the GP process can generate a stock selection model for a low active risk investment style. Compared to a traditional model, the GP model has significantly enhanced future stock return ranking capability. Second, to suit an active investment style, we also use the GP process to generate a model that identifies the stocks with future returns lying in the fat tails of the return distribution. A portfolio constructed based on this model aims to aggressively generate the highest returns possible compared to an index following portfolio. Our tests show that the stock selection power of the GP models is statistically significant. Historical simulation results indicate that portfolios based on GP models outperform the benchmark and the portfolio based on the traditional model. Further, we demonstrate that GP models are more robust in accommodating various market regimes and have more consistent performance than the traditional model.

Abstract: Technical analysis indicators are widely used by traders in financial and commodity markets to predict future price levels and enhance trading profitability. We have previously shown a number of popular indicator-based trading rules to be loss-making when applied individually in a systematic manner. However, technical traders typically use combinations of a broad range of technical indicators. Moreover, successful traders tend to adapt to market conditions by ‘dropping’ trading rules as soon as they become loss-making or when more profitable rules are found. In this paper we try to emulate such traders by developing a trading system consisting of rules based on combinations of different indicators at different frequencies and lags. An initial portfolio of such rules is selected by a genetic algorithm applied to a number of indicators calculated on a set of US Dollar/British Pound spot foreign exchange tick data from 1994 to 1997 aggregated to various intraday frequencies. The genetic algorithm is subsequently used at regular intervals on out-of-sample data to provide new rules and a feedback system is utilized to rebalance the rule portfolio, thus creating two levels of adaptivity. Despite the individual indicators being generally loss-making over the data period, the best rule found by the developed system is found to be modestly, but significantly, profitable in the presence of realistic transaction costs.