[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-152756-105":59,"doc-detail-152756-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","adaptive-model-integration-for-stock-price-forecasting-with-cnn-attn-bilstm","Adaptive Model Integration for Stock Price Forecasting With CNN-ATTN-BiLSTM","","Stock price prediction is challenging due to market volatility and complex nonlinear dynamics that traditional time series methods often fail to model effectively. This study introduces an adaptive model fusion framework combining CNN, bidirectional BiLSTM, and attention to perform multi-scale feature extraction across multiple time horizons. A dynamic fusion mechanism re-weights sub-model contributions based on input data. Experiments using Nasdaq 100 stocks evaluate univariate and multivariate settings, showing improved accuracy and generalization across sectors.",{"@graph":69,"@context":122},[70,84,105],{"@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/adaptive-model-integration-for-stock-price-forecasting-with-cnn-attn-bilstm/152756/",{"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/adaptive-model-integration-for-stock-price-forecasting-with-cnn-attn-bilstm/152756.png","ImageObject",300,407,{"name":92,"@type":93},"Ivy","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-08-27",true,{"@type":102,"interactionType":103,"userInteractionCount":46},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What challenges make stock price forecasting difficult?","Question",{"text":112,"@type":113},"Stock prices exhibit high volatility, non-stationarity, and complex nonlinear patterns, which reduce the ability of many traditional forecasting methods to capture market dynamics.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed CNN-ATTN-BiLSTM adaptive framework work?",{"text":117,"@type":113},"It extracts multi-scale features using CNNs enhanced with attention, then applies an adaptive fusion mechanism that dynamically adjusts each sub-model’s contribution based on the input data.",{"name":119,"@type":110,"acceptedAnswer":120},"Does the method perform differently with univariate versus multivariate data?",{"text":121,"@type":113},"The study investigates both settings and analyzes how data distribution characteristics influence forecasting accuracy, reporting improved performance compared with traditional approaches.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},152756,1787866931,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":46,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":56,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143,"preview_page_count":4},549758252649,"https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819","Journal of Forecasting   \n RESEARCH ARTICLE  \nAdaptive Model Integration for Stock Price Forecasting With CNN-ATTN-BiLSTM  \nYi Xiao1 | Chen He1  | Ming Yi1 | Yi Hu2  \n1School of Information Management, Central China Normal University, Wuhan, P. R. China | 2School of Economics and Management, University of Chinese Academy of Sciences, Beijing, P. R. China  \nCorrespondence: Yi Xiao ([yxiao@ccnu.edu.cn](yxiao@ccnu.edu.cn)) | Ming Yi ([yiming0415@ccnu.edu.cn](yiming0415@ccnu.edu.cn))  \nReceived: 20 April 2025 | Revised: 18 October 2025 | Accepted: 23 December 2025  \nKeywords: adaptive model integration | CNN-ATTN-BiLSTM | Nasdaq 100 | stock price prediction | time series forecasting  \nABSTRACT  \nStock price prediction is challenging due to the high volatility and complex nonlinear patterns in financial markets. Traditional time series forecasting methods often struggle to capture such intricate dynamics. To address this, we propose a novel adaptive model fusion framework that integrates Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory networks (BiLSTM), and Attention Mechanisms (ATTN) to improve stock price forecasting. Our approach employs multi-scale feature extraction using multiple CNNs enhanced with attention to adaptively select relevant features across different time horizons. An adaptive fusion mechanism dynamically adjusts the contribution of each sub-model according to input data, optimizing predictions under varying market conditions. We investigated the effects of both univariate and multivariate data on model performance, and analyze how data distribution characteristics influence forecasting accuracy. Experiments were conducted on stock data from the top 9 companies in the Nasdaq 100 index by market capitalization, validating the robustness and effectiveness of our method across different sectors. Results show that our model significantly outperformed traditional forecasting approaches, achieving higher accuracy and improved generalization in diverse market environments. This study offers a novel framework for stock price prediction and provides valuable insights into adaptive model integration for financial time series forecasting.  \n1 | Introduction  \nFinancial time series forecasting is a critical element of quantitative investment strategies, with stock price prediction playing a central role. Advances in this domain have drawn considerable attention across sectors. For investors, accurate forecasts can optimize decision-making, improve portfolio returns, and mitigate losses. For regulators, timely interventions informed by reliable predictions can help avert market disruptions such as flash crashes, thereby enhancing market stability and efficiency.  \nFormally, the stock price prediction task can be defined as learning a function f that maps a historical sequence of 􀀟  \nobservations to a future value. In its simplest univariate form, this is  \n̂Pt+1 = f (Pt , Pt−1 ,…, Pt−􀀞+1) (1)  \nwhere ̂Pt+1 is the predicted price at time t + 1, and Pi denotes the historical price at time i. More generally, in a multivariate setting that incorporates additional relevant financial data beyond the historical price series, the function extends to  \n̂Pt+1 = f (Xt , Xt−1 ,…, Xt−􀀞+1) (2)  \nwhere Xi ∈ ℝd is a feature vector at time i.  \n© 2026 John Wiley & Sons Ltd.  \nJournal of Forecasting, 2026; 45:1331–1349 1331  \n[https://doi.org/10.1002/for.70098](https://doi.org/10.1002/for.70098)  \nThe academic origins can be traced to the efficient market hypothesis (EMH) (Fama 1970) . The EMH posits that stock prices follow a random walk, suggesting that consistent and exploitable prediction is exceedingly difficult, as prices rapidly incorporate all available information. However, Behavioral Finance research challenges this view, emphasizing the role of psychological biases, information asymmetry, and market anomalies (Shiller 2003) . These inefficiencies often induce detectable patterns in stock data, opening avenu","cbCaijUhoCYlVWBp","https://ap.wps.com/l/cbCaijUhoCYlVWBp","pdf",5038308,"English","# Introduction\n## Problem formulation for stock price forecasting\n## Related work: classical models and machine learning\n## Related work: deep learning and attention-based methods\n## Data processing strategies: transformations and decomposition","[{\"question\":\"What challenges make stock price forecasting difficult?\",\"answer\":\"Stock prices exhibit high volatility, non-stationarity, and complex nonlinear patterns, which reduce the ability of many traditional forecasting methods to capture market dynamics.\"},{\"question\":\"How does the proposed CNN-ATTN-BiLSTM adaptive framework work?\",\"answer\":\"It extracts multi-scale features using CNNs enhanced with attention, then applies an adaptive fusion mechanism that dynamically adjusts each sub-model’s contribution based on the input data.\"},{\"question\":\"Does the method perform differently with univariate versus multivariate data?\",\"answer\":\"The study investigates both settings and analyzes how data distribution characteristics influence forecasting accuracy, reporting improved performance compared with traditional approaches.\"}]","Adaptive Model Integration for Stock Price Forecasting With CNN-ATTN-BiLSTM | PDF",48]