Incorporating Markov decision process on genetic algorithms to formulate trading strategies for stock markets
學年 105
學期 2
出版（發表）日期 2017-03-01
作品名稱 Incorporating Markov decision process on genetic algorithms to formulate trading strategies for stock markets
作品名稱（其他語言）
著者 Chang, Ying-Hua; Lee, Ming-Sheng
單位
出版者
著錄名稱、卷期、頁數 Applied Soft Computing 52, p.1143–1153
摘要 tWith the arrival of low interest rates, investors entered the stock market to seek higher returns. However,the stock market proved volatile, and only rarely could investors gain excess returns when trading in realtime. Most investors use technical indicators to time the market. However the use of technical indica-tors is associated with problems, such as indicator selection, use of conflicting versus similar indicators.Investors thus have difficulty relying on technical indicators to make stock market investment decisions.This research combines Markov decision process and genetic algorithms to propose a new analyticalframework and develop a decision support system for devising stock trading strategies. This investiga-tion uses the prediction characteristics and real-time analysis capabilities of the Markov decision processto make timing decisions. The stock selection and capital allocation employ string encoding to expressdifferent investment strategies for genetic algorithms. The parallel search capabilities of genetic algo-rithms are applied to identify the best investment strategy. Additionally, when investors lack sufficientmoney and stock, the architecture of this study can complete the transaction via credit transactions.The experiments confirm that the model presented in this research can yield higher rewards than otherbenchmarks.
關鍵字 Markov decision processes, Genetic algorithms, Stock selection, Market timing, Capital allocation, Portfolio optimization
語言 en_US
ISSN
期刊性質 國外
收錄於 SCI
產學合作
通訊作者 Chang, Ying-Hua
審稿制度 否
國別 USA
公開徵稿
出版型式 ,電子版,紙本
SDGS 優質教育