{"title":"利用强化学习进行高级统计套利","authors":"Boming Ning, Kiseop Lee","doi":"arxiv-2403.12180","DOIUrl":null,"url":null,"abstract":"Statistical arbitrage is a prevalent trading strategy which takes advantage\nof mean reverse property of spread of paired stocks. Studies on this strategy\noften rely heavily on model assumption. In this study, we introduce an\ninnovative model-free and reinforcement learning based framework for\nstatistical arbitrage. For the construction of mean reversion spreads, we\nestablish an empirical reversion time metric and optimize asset coefficients by\nminimizing this empirical mean reversion time. In the trading phase, we employ\na reinforcement learning framework to identify the optimal mean reversion\nstrategy. Diverging from traditional mean reversion strategies that primarily\nfocus on price deviations from a long-term mean, our methodology creatively\nconstructs the state space to encapsulate the recent trends in price movements.\nAdditionally, the reward function is carefully tailored to reflect the unique\ncharacteristics of mean reversion trading.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"162 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Advanced Statistical Arbitrage with Reinforcement Learning\",\"authors\":\"Boming Ning, Kiseop Lee\",\"doi\":\"arxiv-2403.12180\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Statistical arbitrage is a prevalent trading strategy which takes advantage\\nof mean reverse property of spread of paired stocks. Studies on this strategy\\noften rely heavily on model assumption. In this study, we introduce an\\ninnovative model-free and reinforcement learning based framework for\\nstatistical arbitrage. For the construction of mean reversion spreads, we\\nestablish an empirical reversion time metric and optimize asset coefficients by\\nminimizing this empirical mean reversion time. In the trading phase, we employ\\na reinforcement learning framework to identify the optimal mean reversion\\nstrategy. Diverging from traditional mean reversion strategies that primarily\\nfocus on price deviations from a long-term mean, our methodology creatively\\nconstructs the state space to encapsulate the recent trends in price movements.\\nAdditionally, the reward function is carefully tailored to reflect the unique\\ncharacteristics of mean reversion trading.\",\"PeriodicalId\":501139,\"journal\":{\"name\":\"arXiv - QuantFin - Statistical Finance\",\"volume\":\"162 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - Statistical Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2403.12180\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Statistical Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2403.12180","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Advanced Statistical Arbitrage with Reinforcement Learning
Statistical arbitrage is a prevalent trading strategy which takes advantage
of mean reverse property of spread of paired stocks. Studies on this strategy
often rely heavily on model assumption. In this study, we introduce an
innovative model-free and reinforcement learning based framework for
statistical arbitrage. For the construction of mean reversion spreads, we
establish an empirical reversion time metric and optimize asset coefficients by
minimizing this empirical mean reversion time. In the trading phase, we employ
a reinforcement learning framework to identify the optimal mean reversion
strategy. Diverging from traditional mean reversion strategies that primarily
focus on price deviations from a long-term mean, our methodology creatively
constructs the state space to encapsulate the recent trends in price movements.
Additionally, the reward function is carefully tailored to reflect the unique
characteristics of mean reversion trading.