DEEP LEARNING FOR STOCK MARKET TRADING: A SUPERIOR TRADING STRATEGY?

被引：10

作者：

Fister, D. ^{[1
]}

Mun, J. C. ^{[2
]}

Jagric, V ^{[1
]}

Jagric, T. ^{[1
]}

机构：

[1] Univ Maribor, Fac Econ & Business, Razlagova 14, SI-2000 Maribor, Slovenia

[2] Naval Postgrad Sch, 1 Univ Circle, Monterey, CA 93943 USA

来源：

NEURAL NETWORK WORLD | 2019年 / 29卷 / 03期

关键词：

LSTM networks; machine learning; automated stock trading; SHORT-TERM-MEMORY; PREDICTION; CLASSIFICATION; NETWORKS; RETURNS; SYSTEMS;

D O I：

10.14311/NNW.2019.29.011

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Deep-learning initiatives have vastly changed the analysis of data. Complex networks became accessible to anyone in any research area. In this paper we are proposing a deep-learning long short-term memory network (LSTM) for automated stock trading. A mechanical trading system is used to evaluate its performance. The proposed solution is compared to traditional trading strategies, i.e., passive and rule-based trading strategies, as well as machine learning classifiers. We have discovered that the deep-learning long short-term memory network has outperformed other trading strategies for the German blue-chip stock, BMW, during the 2010-2018 period.

引用

页码：151 / 171

页数：21

共 64 条

[1] AN INTRODUCTION TO KERNEL AND NEAREST-NEIGHBOR NONPARAMETRIC REGRESSION [J].