标题:A framework of deep reinforcement learning for stock evaluation functions
作者:Luo, Tai-Li; Wu, Mu-En; Chen, Chien-Ming
通讯作者:Wu, MuEn
作者机构:[Luo, Tai-Li; Wu, Mu-En] Natl Taipei Univ Technol, Dept Informat & Finance Management, Taipei, Taiwan.; [Chen, Chien-Ming] Shandong Univ Sci & Techn 更多
来源:JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
出版年:2020
卷:38
期:5
页码:5639-5649
DOI:10.3233/JIFS-179653
关键词:Deep reinforcement learning; convolution neural networks; evaluation; function; position sizing; money management
摘要:Quantitative trading is a crucial aspect of money management; however, conventional trading strategies are based on indicators and signals, despite the fact that position sizing is arguably the most important issue. In this study, we present a stock evaluation function that outputs the size of the stock in each fixed period as well as the consequences of increasing or decreasing the size of one's position. The difficulties involved in using machine learning to adjust stock weighting can be attributed to difficulties in obtaining definite answers via supervised learning. We therefore train our evaluation function using reinforcement learning via CNN within the EIIE network architecture and have the agent adjust the size of the position with the purpose of maximizing profits. Back testing was performed using the top 50 stocks in Taiwan, based on market capitalization. In experiments, most of the stock returns outperformed conventional strategies in terms of cumulative stock value.
收录类别:EI;SCOPUS;SCIE
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086717015&doi=10.3233%2fJIFS-179653&partnerID=40&md5=fa6dca0af4fb9139d2716c53f9f5545f
TOP