Using genetic algorithms to find technical trading rules

被引：413

作者：

Allen, F ^{[1
]}

Karjalainen, R

机构：

[1] Univ Penn, Wharton Sch, Philadelphia, PA 19104 USA

[2] Merrill Lynch & Co Inc, Mercury Asset Management, London EC4R 9AS, England

来源：

JOURNAL OF FINANCIAL ECONOMICS | 1999年 / 51卷 / 02期

基金：

芬兰科学院; 美国国家科学基金会;

关键词：

trading rules; genetic algorithms; excess returns;

D O I：

10.1016/S0304-405X(98)00052-X

中图分类号：

F8 [财政、金融];

学科分类号：

0202 ;

摘要：

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. (C) 1999 Elsevier Science S.A. All rights reserved.

引用

页码：245 / 271

页数：27

共 31 条

[1]

ALEXANDER SS, 1961, IMR-IND MANAG REV, V2, P7

[2]

ALEXANDER SS, 1964, RANDOM CHARACTER STO, V2, P338

[3]

[Anonymous], INT J POLICY ANAL IN

[4]

BAUER RJ, 1994, GENETIC ALGORITHMS I