[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117161-en":3,"doc-seo-117161-105":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":4,"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},117161,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Selective Machine Learning for Stock Market Prediction - Master of Science Thesis","Selective Machine Learning for Stock Market Prediction applies state-of-the-art machine learning models to forecast stock returns, addressing a key challenge: broad stock coverage introduces substantial noise that degrades performance. The study integrates two mechanisms—Selective Prediction and Curriculum Learning—to improve robustness under noisy data and enhance overall predictive quality. The work also outlines directions for future research applying selective machine learning methods to finance, with a focus on selecting subsets of stocks expected to outperform and improve signal confidence.","Copyright  \nby Jacob Barcelona  \n2024  \n1  \nThe Thesis Committee for Jacob Barcelona certifies that this is the approved version of the following thesis:  \nSelective Machine Learning for Stock Market Prediction  \nSUPERVISING COMMITTEE:  \nGreg Plaxton, Supervisor  \nKumar Muthuaraman, Co-supervisor  \nSelective Machine Learning for Stock Market Prediction  \nby  \nJacob Barcelona  \nThesis  \nPresented to the Faculty of the Graduate School of The University of Texas at Austin  \nin Partial Fulfillment  \nof the Requirements  \nfor the Degree of  \nMaster of Science in Computer Science  \nThe University of Texas at Austin May 2024  \nAbstract  \nSelective Machine Learning for Stock Market Prediction  \nJacob Barcelona, MSCS  \nThe University of Texas at Austin, 2024  \nSUPERVISORS: Greg Plaxton, Kumar Muthuaraman  \nApplying state-of-the-art machine learning models to predicting stock returns has been a common focus of research for practitioners. However, these models often face challenges due to the inclusion of a wide universe of stocks, leading to performance degradation caused by significant noise. In this study, we apply two mechanisms from Selective Machine Learning and Curriculum Learning to enhance the robustness of our model to noise and improve overall performance. Additionally, we explore several avenues for future research in selective machine learning within the domain of finance.  \nTable of Contents  \nChapter 1: Introduction ............................. 6  \nChapter 2: The Selective Prediction Problem .................. 11  \nChapter 3: Data .................................. 13  \nChapter 4: Model ................................. 16  \nChapter 5: Methodology ............................. 18  \nChapter 6: Results and Analysis ......................... 22  \nChapter 7: Conclusion and Future Work .................... 28  \nAppendix ...................................... 30  \nWorks Cited ..................................... 31  \nVita ......................................... 33  \nChapter 1: Introduction  \nThe task of predicting stock movements has been at the center of financial research since its inception. As machine learning has become more advanced, many papers have been focused on applying new models to this task. While some success has been found, past research has treated the directional stock classification task no different than other machine learning tasks. When making predictions on images or text, a general model with substantial breadth is important for generating new sequences for user inputs, as seen in sequence-to-sequence models. In stock classification, however, the objective is to construct high-performing portfolios based on the signals provided by our models in each period. This task involves identifying signals amidst the noise of the stochastic movements of the stock market. The goal is to select a subset of stocks that are predicted to outperform the majority of the market for a given period. Given this, the breadth of our model is of little importance to us because standard practice has us ranking the predictions of the model, and selecting the top picks to form a portfolio. Because of this the majority of predictions we make that won’t be used and make a more general model than is practical. Each period, ifour goal is to create a portfolio with the highest chance at getting an excess return we mostly care about the tails of the returns distribution.  \nCountless papers and firms in industry have attempted to apply machine learning to predict the movement of stock returns. Recently, with the emergence of more advanced neural network models like Long Short-Term Memory (LSTM) and Transformer, researchers have begun applying these models to the task of predicting stock movements. The hope is that because LTSMs and Transformers are good at relating long and short term patterns they could find an edge that previous models could not.  \nIn Fischer and Krauss (2017) and Guijarro-Ordonez et al. (2022), LTSM networks and CNN","cbCaiaST2727NMPz","https://ap.wps.com/l/cbCaiaST2727NMPz","pdf",319980,1,33,"English","en",105,"# Chapter 1: Introduction\n# Chapter 2: The Selective Prediction Problem\n# Chapter 3: Data\n# Chapter 4: Model\n# Chapter 5: Methodology\n# Chapter 6: Results and Analysis\n# Chapter 7: Conclusion and Future Work\n# Appendix\n# Works Cited\n# Vita","[{\"question\":\"What problem does the thesis address in stock market prediction?\",\"answer\":\"It addresses performance degradation caused by significant noise when using machine learning models across a wide universe of stocks, which dilutes predictive signals.\"},{\"question\":\"How does the thesis improve model robustness?\",\"answer\":\"It applies mechanisms from Selective Machine Learning and Curriculum Learning to make the model more robust to noise and improve overall performance.\"},{\"question\":\"Why is selective prediction useful for portfolio construction?\",\"answer\":\"Because the goal is to identify signals for a specific period and select a subset of stocks predicted to outperform, focusing on the return distribution tails where excess-return opportunities lie.\"}]","Selective Machine Learning for Stock Market Prediction - Master of Science Thesis | PDF",1785674169,83,{"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},"selective-machine-learning-for-stock-market-prediction-master-of-science-thesis","",{"@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/selective-machine-learning-for-stock-market-prediction-master-of-science-thesis/117161/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in stock market prediction?","Question",{"text":75,"@type":76},"It addresses performance degradation caused by significant noise when using machine learning models across a wide universe of stocks, which dilutes predictive signals.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis improve model robustness?",{"text":80,"@type":76},"It applies mechanisms from Selective Machine Learning and Curriculum Learning to make the model more robust to noise and improve overall performance.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is selective prediction useful for portfolio construction?",{"text":84,"@type":76},"Because the goal is to identify signals for a specific period and select a subset of stocks predicted to outperform, focusing on the return distribution tails where excess-return opportunities lie.","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"]