[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-152754-105":59,"doc-detail-152754-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","a-hybrid-forecasting-model-based-on-deep-learning-feature-extraction-and-statistical-arbitrage-methods-for-stock-trading-strategies","A hybrid forecasting model based on deep learning feature extraction and statistical arbitrage methods for stock trading strategies","","Financial market time series exhibit nonlinearity from rapid data accumulation, making stock price prediction difficult. This study proposes a quantitative trading strategy that integrates basic quantitative trading arbitrage rules with deep learning feature extraction. It builds a hybrid signal-trading system where a genetic algorithm optimizes parameters for a moving-average timing indicator, while a CNN-Bi-LSTM with attention and a modified loss function improves local optimization of trading signals. Tests on China A-shares show moving-average-only arbitrage is ineffective, while the optimized deep learning framework significantly increases profit, annualized revenue, winning rate, and maintains robustness under simulated transaction costs.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-hybrid-forecasting-model-based-on-deep-learning-feature-extraction-and-statistical-arbitrage-methods-for-stock-trading-strategies/152754/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-hybrid-forecasting-model-based-on-deep-learning-feature-extraction-and-statistical-arbitrage-methods-for-stock-trading-strategies/152754.png","ImageObject",300,407,{"name":92,"@type":93},"Ivy","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-08-27",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",24,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is stock price prediction considered challenging in this study?","Question",{"text":113,"@type":114},"Financial market time series are nonlinear due to rapid data accumulation, which makes prediction difficult.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What is the proposed hybrid forecasting and trading framework?",{"text":118,"@type":114},"The approach combines basic quantitative trading arbitrage rules with deep learning feature extraction and uses a genetic algorithm to optimize moving-average timing parameters.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the CNN-Bi-LSTM model contribute to improving trading performance?",{"text":122,"@type":114},"The CNN-Bi-LSTM with attention and a modified loss function optimizes trading signals by learning local trends of price fluctuations and correcting signals using prediction results.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},152754,1787866919,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},549758252649,"https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819","Received: 28 June 2021 Revised: 15 February 2023 Accepted: 19 March 2023  \nDOI: 10.1002/for.2978  \nRESE ARCH ARTICL E  \nA hybrid forecasting model based on deep learning feature extraction and statistical arbitrage methods for stock trading strategies  \nWeiqian Zhang 1  | Songsong Li 1 | Zhichang Guo 2 | Yizhe Yang 2  \n1School of Management, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin City, Heilongjiang Province, China  \n2School of Mathematics, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin City, Heilongjiang Province, China  \nCorrespondence  \nSongsong Li, School of Management, Harbin Institute of Technology, No. 92 West Dazhi Street, Nangang District, Harbin City, Heilongjiang Province, China.  \nEmail: [lisongsong@hit.edu.cn](lisongsong@hit.edu.cn)  \nFunding information Heilongjiang Postdoctoral Scientific Research Developmental Fund,  \nGrant/Award Number: LBH-Q18064; National Natural Science Foundation of China, Grant/Award Number: 71773024; Natural Science Foundation of Heilongjiang Province of China, Grant/Award Number: G2018006  \nAbstract  \nThe time series data of financial markets are nonlinear, owing to rapid data accumulation. Thus, research on stock price prediction has always been a challenge. This study proposes a quantitative trading strategy that combines basic quantitative trading rules and deep learning methods to help investors realize arbitrage. We combine basic quantitative trading arbitrage with deep learning frameworks to fully extract market characteristics and develop trading strategies for investors. The hybrid forecasting model is a new signal-trading system that uses a genetic algorithm to obtain optimal parameters for the technical indicator timing method of the moving average price. The deep learning structure of the CNN-Bi-LSTM, with the attention mechanism and modified loss function, optimizes the trading signal to achieve local optimization. Its core concept is to determine the trading signal through the local trend of price fluctuations and then correct the trading signal through the prediction results. A-shares in the Chinese market trading data are used asthe statistical arbitrage analysis process to output actual trading signals and verify the effectiveness of the system. The results demonstrate that an arbitrage strategy based only on moving average trading rules is ineffective. With the optimization of the deep learning CNN-Bi-LSTM framework, the arbitrage ability improves significantly. The optimized strategy can increase the final profit by 1.6042 to the greatest extent. The annualized revenue increased by 35.16%, and the winning rate increased by 15.22% . In addition, we consider the transaction costs during the simulated transaction process. An optimized trading strategy can effectively seize arbitrage opportunities; hence, its profitability and stability are significantly improved.  \nKEYWOR DS  \ndeep learning, feature extraction, hybrid forecasting, statistical arbitrage, stock trading strategy  \nJournal of Forecasting. 2023;1–21.  \n[wileyonlinelibrary.com/journal/for](wileyonlinelibrary.com/journal/for)  \n© 2023 John Wiley & Sons Ltd.  \n1  \n1 | INTRODUCTION  \nTrading rules define when to buy and sell the profit pursued by each operation and seize arbitrage opportunities. Based on moving averages, golden crosses, death crosses, resistance lines, and support lines, the corresponding concepts are summarized using a physics background to measure market changes (Ausloos & Ivanova, 2002) . The validity of technical indicators has also been tested, and it was found that once transaction costs are included, transaction profits will be eliminated. Simple moving average index trading rules cannot beat the standard buy and hold strategy of the China Stock Exchange index (Zhu et al., 2015) . When examining the daily stock prices and trading volume of 39 constituent stocks in the Shenzhen Stock Exchange A-Share Index of Chin","cbCaiavikvmKaO5X","https://ap.wps.com/l/cbCaiavikvmKaO5X","pdf",2601083,21,"English","# Introduction\n## Technical indicators and transaction cost considerations\n## Stock market uncertainty and prediction approaches\n## Technical vs fundamental analysis\n## Arbitrage and volatility prediction background","[{\"question\":\"Why is stock price prediction considered challenging in this study?\",\"answer\":\"Financial market time series are nonlinear due to rapid data accumulation, which makes prediction difficult.\"},{\"question\":\"What is the proposed hybrid forecasting and trading framework?\",\"answer\":\"The approach combines basic quantitative trading arbitrage rules with deep learning feature extraction and uses a genetic algorithm to optimize moving-average timing parameters.\"},{\"question\":\"How does the CNN-Bi-LSTM model contribute to improving trading performance?\",\"answer\":\"The CNN-Bi-LSTM with attention and a modified loss function optimizes trading signals by learning local trends of price fluctuations and correcting signals using prediction results.\"}]","A hybrid forecasting model based on deep learning feature extraction and statistical arbitrage methods for stock trading strategies | PDF",53]