A genetic algorithm (GA) is a search technique that falls within the intersection of optimization algorithms and evolutionary algorithms. GAs became a widely recognized optimization method as a result of the work of John Holland in the early 1970s (Holland, 1975). On average, genetic algorithms are no better or worse than any other search algorithm (Wolpert and Macready, 1995).
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.
This paper proposes genetic algorithms (GAs) approach to feature discretization and the determination of connection weights for artificial neural networks (ANNs) to predict the stock price index. Previous research proposed many hybrid models of ANN and GA for the method of training the network, feature subset selection, and topology optimization. In most of these studies, however, GA is only used to improve the learning algorithm itself. In this study, GA is employed not only to improve the learning algorithm, but also to reduce the complexity in feature space. GA optimizes simultaneously the connection weights between layers and the thresholds for feature discretization. The genetically evolved weights mitigate the well-known limitations of the gradient descent algorithm. In addition, globally searched feature discretization reduces the dimensionality of the feature space and eliminates irrelevant factors. Experimental results show that GA approach to the feature discretization model outperforms the other two conventional models.
Expert Systems with Applications, Volume 19, Number 2, August 2000, pp. 125-132(8)
ME: The study compares a GA approach to feature discretization, the linear transformation with the backpropagation neural network and the linear transformation with ANN trained by GA and found that the first method outperfrmed the other two conventional models.
COLIN, Andrew M., 1994. 'Genetic Algorithms for Financial Modelling', In: Trading on the edge: neural, genetic and fuzzy …. [Cited by 11] (0.95/year)
CHORAFAS, D.N., 1994. Chaos Theory in the financial markets: applying fractals, fuzzy logic, genetic algorithms, swarm simulation & the Monte Carlo Method to Manage Market Chaos and Volatility. Chicago, Ill.: Probus Pub. Co. [Cited by 11] (0.95/year)
BAUER, J.R.J. and G.E. LIEPINS, 1991. Genetic algorithms and stock market timing trading rules. Proceedings of the 11th International Symposium on …. [Cited by 4] (0.27/year)
BAUER, Richard, Jr. "An Introduction to Genetic Algorithms: A Mutual Fund Screening Example," NeuroVe$t Journal, Vol.2, No.4,Jul/Aug 1994, pp. 16-19.
BORASKY, M. Edward, Preliminary Design of A Personal Trading System, Nonlinear Financial Forecasting - Proceedings of the First INFFC, edited by Randall B. Caldwell
CHAN, Kin On and Kin Hong CHEUNG, Application of Genetic Algorithms in Stock Market Prediction.
FARLEY, Arthur M. and Christopher B. BORNMANN, Using a Genetic Algorithm to Determine a Prediction Function for Stock Prices, Nonlinear Financial Forecasting - Proceedings of the First INFFC, edited by Randall B. Caldwell
HARLAND, Zac, Trading a 2 year old – the Real-time Performance of a Neurogenetic T-bond Futures Trading System.
KORCZAK, Jerzy, et al., Genetic Evolution of Neural Network Models for Financial Market Forecasting, Nonlinear Financial Forecasting - Proceedings of the First INFFC, edited by Randall B. Caldwell
OLIKER, Shai, A Distributed Genetic Algorithm for Designing and Training Modular Neural Networks in Financial Prediction, Nonlinear Financial Forecasting - Proceedings of the First INFFC, edited by Randall B. Caldwell
SZETO, K.Y. and K.H. CHEUNG, lip;. Application of genetic algorithms in stock market prediction. Weigend, AS et al.: Decision Technologies for Financial &h. [Cited by 5] (?/year)
SZETO, K.Y., K.O. CHAN and K.H. CHEUNG, Application of Genetic Algorithms in Stock Market Prediction, Proc. of the Fourth International Conference on Neural Networks in the Capital Markets (NNCM-96), pp. 95-103, 1997.
WONG F., "Hybrid Systems of Neural Network, Fuzzy Logic and Genetic Algorithms", in Advanced Technology for Trading, Portfolio and Risk Management, Edited by Dr. Guido Deboeck, Advanced Analytical Laboratory, Investment Dept., World Bank.
WONG F., Tan P., "Neural Networks and Genetic Algorithm For Economic Forecasting", AI in Economics and Business Administration, Ed. I.H. Daniels & Feelders, Netherland.