[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119618-en":3,"doc-seo-119618-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119618,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Predicting Stock Returns With Machine Learning - Global Versus Sector Models","Recent research shows non-linear machine learning models, including neural networks, outperform traditional linear approaches when forecasting cross-sectional stock returns. This thesis examines whether sector-specific neural networks can uncover sector-related relationships and beat a single global neural network. Predictive performance is evaluated at both the individual stock level and in portfolios built from return forecasts, including long-short strategies formed from ranked predictions. Results indicate a global neural network trained on pooled data dominates across the US market, while sector-specific models do not provide an advantage, particularly early in the out-of-sample period.","Junior Management Science 10(3) (2025) 561-581  \n\n|  | Junior Management Science\u003Cbr>[www.jums.academy](www.jums.academy)\u003Cbr>[ISSN: 2942-1861](ISSN: 2942-1861) | \u003Cbr> Volume 10, Issue 3, September 2025 DOMINIK VAN Editor:AAKEN JUNIOR\u003Cbr>Advisory Editorial Board:\u003Cbr>FREDERIK AHLEMANN\u003Cbr>JANTHOMASMARKUS-PHILIPP AHRENSBAHLINGERBECKMANN MANAGEMENT\u003Cbr>SULEIKA BORT\u003Cbr>ROLF BRÜHL\u003Cbr>KATRIN BURMEISTERCATHERINE CLEOPHASNILS CRASSELT-LAMP SCIENCE\u003Cbr>BENEDIKT DOWNAR\u003Cbr>KERSTIN FEHRE\u003Cbr>MATTHIAS FINKDAVID FLORYSIAK Johannes Witter, Predicting Stock Returns With Machine 561 GUNTHER FRIEDL Learning: Global Versus Sector Models\u003Cbr>MARTIN FRIESL\u003Cbr>FRANZ FUERST\u003Cbr>WOLFGANG GÜTTEL Robin Roskosch, Beware of Bullshit – A Qualitative Study on 582 NINAANNEKATRIN HANSENKATARINA HEIDER Young Adults’ Sustainability Awareness of Online\u003Cbr>CHRISTIAN HOFMANN Services\u003Cbr>SVEN HÖRNER\u003Cbr>STEPHAN KAISER\u003Cbr>NADINE KAMMERLANDER Nadhilla Mazaya, Board Gender Diversity: Evidence From 609\u003Cbr>ALFRED KIESER\u003Cbr>ALEKSANDRA KLEIN Indonesia\u003Cbr>NATALIA KLIEWER\u003Cbr>DODO ZU KNYPHAUSEN-AUFSESS\u003Cbr>SABINE T. KÖSZEGI Alexander Sake, Value Creation Opportunities of Generative 631 ARJAN KOZICACHRISTIAN KOZIOL AI – A Case Study\u003Cbr>MARTIN KREEB\u003Cbr>HANS-WERNER KUNZULRICH KÜPPER Justus Olbrich, The Effect of Changes in Internal Control 657\u003Cbr>MICHAEL MEYER Systems on Audit Risk\u003Cbr>JÜRGEN MÜHLBACHER\u003Cbr>GORDON MÜLLER-SEITZ\u003Cbr>J. PETER MURMANN Jan Oliver Horstmann Mandatory ESG Disclosure and Firm 677 ANDREAS OSTERMAIER\u003Cbr>BURKHARD PEDELL Value – A Quantitative Analysis of the Effect of\u003Cbr>MARCELARTHUR POSCHPROKOPCZUK Directive 2014/95/EU on Firm Value\u003Cbr>TANJA RABL\u003Cbr>NICOLE SASCHARATZINGERRAITHEL-SAKEL Meret Anna Gläser Government Interventions During the 715 ASTRID REICHEL COVID-19 Pandemic, Culture, and Corporate Cost\u003Cbr>KATJA ROST Behaviour\u003Cbr>THOMAS RUSSACK\u003Cbr>FLORIAN SAHLING\u003Cbr>MARKOANDREAS GSARSTEDTSCHERER Zewei Shi, Modeling the Impact of Emission Credit Systems on 748 STEFAN SCHMID Automotive Product Portfolios: A Mathematical\u003Cbr>UTE SCHMIEL\u003Cbr>CHRISTIAN SCHMITZ Analysis of Policy Effects in Europe, China, and the\u003Cbr>MARTIN SCHNEIDERMARKUS SCHOLZ U.S. Under Different Demand Scenarios\u003Cbr>LARS SCHWEIZER\u003Cbr>THORSTENDAVID SEIDLSELLHORN Hagen Alexander Hönerloh, Numerical Studies for the 781\u003Cbr>STEFAN SEURING Scheduling of Continuous Annealing Lines\u003Cbr>VIOLETTA SPLITTER\u003Cbr>ANDREAS SUCHANEK\u003Cbr>TILL TALAULICAR Lea Wedel KPIs for Sustainability: Defining the Strategy for a 810\u003Cbr>ANN TANKANJA TUSCHKE Sustainable Future in the Insurance Industry\u003Cbr>MATTHIAS UHL\u003Cbr>CHRISTINE VALLASTER\u003Cbr>PATRICK VELTE\u003Cbr>CHRISTIAN VÖGTLIN\u003Cbr>BARBARA E. WEISSENBERGER\u003Cbr>ISABELL M. WELPE\u003Cbr>HANNES WINNER\u003Cbr>THOMAS WRONA\u003Cbr>THOMAS ZWICK Published by Junior Management Science e.V.\u003Cbr>This is an Open Access article distributed under the terms of the CC-BY-4.0 (Attribution 4.0 International) . Open Access funding provided by ZBW.\u003Cbr>ISSN: 2942-1861 |\n| --- | --- | --- |\n| Predicting Stock Returns With Machine Learning: Global Versus Sector Models\u003Cbr>Johannes Witter\u003Cbr>Technical University of Munich |  |  |\n| Abstract\u003Cbr>Recent studies highlight the superior performance of non-linear machine learning models, such as neural networks, over traditional linear models in predicting cross-sectional stock returns. These models are capable of capturing complex non-linear interactions between predictive signals and future returns. This thesis researches whether sector-specific neural networks can detect sector-related relationships to outperform a global neural network. It evaluates the predictive power of these models at the stock level and in portfolios based on return forecasts, constructing long-short portfolios from the networks’sorted predictions. A global neural network model trained on the full sample of stocks dominates neural networks trained on individual GICS sectors in predicting the cross-section of US stock returns. Sector-specific neural networks fail to gain an advantage by capturing complex sector-sp","cbCaiqbeZsZ47J2N","https://ap.wps.com/l/cbCaiqbeZsZ47J2N","pdf",1356896,1,21,"English","en",105,"# Introduction\n## Model comparison for cross-sectional return prediction\n## Data sample and evaluation settings","[{\"question\":\"What is the main research question of the thesis?\",\"answer\":\"Whether sector-specific neural networks can detect sector-related relationships and outperform a global neural network in predicting cross-sectional US stock returns.\"},{\"question\":\"How are the models evaluated in the study?\",\"answer\":\"The predictive power is assessed at the stock level and also through portfolios constructed from return forecasts, including long-short portfolios using sorted predictions.\"},{\"question\":\"What are the key findings about global versus sector models?\",\"answer\":\"A global neural network trained on pooled data dominates sector-specific neural networks, and sector-specific models fail to gain an advantage, especially in the early out-of-sample period.\"}]","Predicting Stock Returns With Machine Learning - Global Versus Sector Models | PDF",1785725332,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-stock-returns-with-machine-learning-global-versus-sector-models","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-stock-returns-with-machine-learning-global-versus-sector-models/119618/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main research question of the thesis?","Question",{"text":75,"@type":76},"Whether sector-specific neural networks can detect sector-related relationships and outperform a global neural network in predicting cross-sectional US stock returns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the models evaluated in the study?",{"text":80,"@type":76},"The predictive power is assessed at the stock level and also through portfolios constructed from return forecasts, including long-short portfolios using sorted predictions.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the key findings about global versus sector models?",{"text":84,"@type":76},"A global neural network trained on pooled data dominates sector-specific neural networks, and sector-specific models fail to gain an advantage, especially in the early out-of-sample period.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]