Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future

Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future

碩士 === 國立臺灣大學 === 資訊工程學研究所 === 97 === This thesis applied Q-learning algorithm of reinforcement learning to improve a simple intra-day trading system of Taiwan stock index future. We simulate the performance of the original strategy by back-testing it with historical data. Furthermore, we use histor...

Full description

Bibliographic Details
Main Authors: Ching-Pin Lin, 林敬斌
Other Authors: 呂育道
Format: Others
Language:zh-TW
Published: 2009
Online Access:http://ndltd.ncl.edu.tw/handle/34369847383488676186
id ndltd-TW-097NTU05392037
record_format oai_dc
spelling ndltd-TW-097NTU053920372016-05-04T04:31:31Z http://ndltd.ncl.edu.tw/handle/34369847383488676186 Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future 使用增強式學習法改善一個簡易的臺灣股價指數期貨當沖交易系統 Ching-Pin Lin 林敬斌 碩士 國立臺灣大學 資訊工程學研究所 97 This thesis applied Q-learning algorithm of reinforcement learning to improve a simple intra-day trading system of Taiwan stock index future. We simulate the performance of the original strategy by back-testing it with historical data. Furthermore, we use historical information as training data for reinforcement learning and examine the improved achievement. The training data are the tick data of every trading day from 2003 to 2007 and the testing period is from January 2008 to May 2009. The original strategy is a trend-following channel breakout system. We take the result of reinforcement learning to determine whether to do trend following or countertrend trading every time the system plans to make position. 呂育道 2009 學位論文 ; thesis 17 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立臺灣大學 === 資訊工程學研究所 === 97 === This thesis applied Q-learning algorithm of reinforcement learning to improve a simple intra-day trading system of Taiwan stock index future. We simulate the performance of the original strategy by back-testing it with historical data. Furthermore, we use historical information as training data for reinforcement learning and examine the improved achievement. The training data are the tick data of every trading day from 2003 to 2007 and the testing period is from January 2008 to May 2009. The original strategy is a trend-following channel breakout system. We take the result of reinforcement learning to determine whether to do trend following or countertrend trading every time the system plans to make position.
author2 呂育道
author_facet 呂育道
Ching-Pin Lin
林敬斌
author Ching-Pin Lin
林敬斌
spellingShingle Ching-Pin Lin
林敬斌
Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future
author_sort Ching-Pin Lin
title Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future
title_short Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future
title_full Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future
title_fullStr Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future
title_full_unstemmed Using Reinforcement Learning to Improve a Simple Intra-day Trading System of Taiwan Stock Index Future
title_sort using reinforcement learning to improve a simple intra-day trading system of taiwan stock index future
publishDate 2009
url http://ndltd.ncl.edu.tw/handle/34369847383488676186
work_keys_str_mv AT chingpinlin usingreinforcementlearningtoimproveasimpleintradaytradingsystemoftaiwanstockindexfuture
AT línjìngbīn usingreinforcementlearningtoimproveasimpleintradaytradingsystemoftaiwanstockindexfuture
AT chingpinlin shǐyòngzēngqiángshìxuéxífǎgǎishànyīgèjiǎnyìdetáiwāngǔjiàzhǐshùqīhuòdāngchōngjiāoyìxìtǒng
AT línjìngbīn shǐyòngzēngqiángshìxuéxífǎgǎishànyīgèjiǎnyìdetáiwāngǔjiàzhǐshùqīhuòdāngchōngjiāoyìxìtǒng
_version_ 1718259434024599552

Similar Items