[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117072-en":3,"doc-seo-117072-105":30,"detail-sidebar-cat-0-en-105":92},{"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},117072,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Stock picking with machine learning","The study analyzes machine learning algorithms for stock selection by training models on weekly data from historical S&P 500 constituents between January 1999 and March 2021. It uses typical equity factors, additional firm fundamentals, and technical indicators to predict whether an individual stock will outperform or underperform the cross-sectional median return over the next week. Trading strategies buy stocks with the highest predicted outperformance probability. Results show significant outperformance versus an equally weighted benchmark, with regularized logistic regression performing comparably to more complex models and robustness confirmed on STOXX Europe 600.","DOI: 10.1002/for.3021  \nRESE ARCH ARTICL E  \nStock picking with machine learning  \nDominik Wolff1,2,3  | Fabian Echterling 4  \n1Deka Investment GmbH, Frankfurt, Germany  \n2University of Applied Sciences, Frankfurt, Germany  \n3Technical University Darmstadt, Darmstadt, Germany  \n4Allianz Global Investors, Frankfurt, Germany  \nCorrespondence  \nDominik Wolff, Technical University of Darmstadt, Hochschulstraße 1, 64289  \nDarmstadt, Germany.  \nEmail: dominik.wolff@deka.de  \nFunding information Deka Investment GmbH  \nAbstract  \nWe analyze machine learning algorithms for stock selection. Our study buildson weekly data for the historical constituents of the S&P500 over the period from January 1999 to March 2021 and builds on typical equity factors, additional firm fundamentals, and technical indicators. A variety of machine learning models are trained on the binary classification task to predict whether a specific stock outperforms or underperforms the cross-sectional median return over the subsequent week. We analyze weekly trading strategies that invest in stocks with the highest predicted outperformance probability. Our empirical results show substantial and significant outperformance of machine learningbased stock selection models compared to an equally weighted benchmark. Interestingly, we find more simplistic regularized logistic regression models to perform similarly well compared to more complex machine learning models. The results are robust when applied to the STOXX Europe 600 as alternative asset universe.  \nKEYWOR DS  \nequity portfolio management, investment decisions, machine learning, neural networks, stock picking, stock selection  \n1 | INTRODUCTION  \nMachine learning (ML) gained immense importance during the last decade mainly due to three reasons: the availability of computational power, improvements in ML algorithms, and the availability of large datasets, which are required to train complex models. While ML has increasingly attracted the attention of the asset management industry and the finance literature alike, the use of ML methodologies in portfolio management is still very limited.  \nThe views expressed in this paper are those of the authors and do not necessarily reflect those of Deka Investment GmbH or its employees.  \nIn this study, we combine insights from ML and finance research and analyze the potential of different ML algorithms for an important portfolio management task: predicting the relative returns of individual stocks. While earlier literature focuses on predicting equity market returns, we analyze the weekly predictability of the relative stock performance. More specifically, we group stocks based on their weekly relative performance and try to forecast outperforming versus underperforming stocks in a binary classification task.1  \nGiven the immense amount of data available and the complex and potential nonlinear relations in the data, ML models might be very well suited for that task. In contrast to linear models, ML models can “learn” nonlinear relationships and even interactions between  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2023 The Authors. Journal of Forecasting published by John Wiley & Sons Ltd.  \npredictors without specifying the underlying model. Therefore, in the presence of nonlinearities and the availability of large training sets, ML approaches might improve stock selection compared to linear models. Because most ML models tend to do better on classification problems rather than on regression problems, we focus on the binary classification of stocks into outperformer and underperformer rather than on forecasting returns of individual stocks as point estimates.  \nWe empirically analyze deep neural networks (DNNs), long short-term memory (LSTM) neural networks (NNs), random forest (RF), gradient boosting, and regularize","cbCaiiPvW6TUMPxT","https://ap.wps.com/l/cbCaiiPvW6TUMPxT","pdf",1642063,1,22,"English","en",105,"# Introduction\n## Machine learning in portfolio management\n## Weekly relative stock performance prediction\n## Binary classification and model training\n## Empirical asset universe and performance evaluation","[{\"question\":\"How does the study define the prediction target for stock selection?\",\"answer\":\"Stocks are classified into outperformers or underperformers using the cross-sectional median return as a threshold. The models then predict whether a stock will outperform or underperform over the subsequent week.\"},{\"question\":\"Which machine learning models are evaluated in the analysis?\",\"answer\":\"The study trains deep neural networks, LSTM neural networks, random forests, gradient boosting, and regularized logistic regression, using stock characteristics as inputs.\"},{\"question\":\"What trading strategy results from the model predictions?\",\"answer\":\"Each week, the strategy invests in stocks with the highest predicted probability of outperforming, based on the models’ classification outputs.\"}]","Stock picking with machine learning | PDF",1785673547,55,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"stock-picking-with-machine-learning","",{"@graph":36,"@context":86},[37,54,69],{"@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/stock-picking-with-machine-learning/117072/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"How does the study define the prediction target for stock selection?","Question",{"text":76,"@type":77},"Stocks are classified into outperformers or underperformers using the cross-sectional median return as a threshold. The models then predict whether a stock will outperform or underperform over the subsequent week.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning models are evaluated in the analysis?",{"text":81,"@type":77},"The study trains deep neural networks, LSTM neural networks, random forests, gradient boosting, and regularized logistic regression, using stock characteristics as inputs.",{"name":83,"@type":74,"acceptedAnswer":84},"What trading strategy results from the model predictions?",{"text":85,"@type":77},"Each week, the strategy invests in stocks with the highest predicted probability of outperforming, based on the models’ classification outputs.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]