[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118587-en":3,"doc-seo-118587-105":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},118587,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","CONSTRUCTION OF STOCK PORTFOLIOS BY MACHINE LEARNING METHODS - Master Thesis 2025: 17","Study of two machine learning methods, Long-Short Term Memory networks (LSTM) and Random Forest, combining mathematical foundations such as gradient descent, automatic differentiation, and recurrent neural network theory. For application, the work constructs U.S. stock portfolios using technical and/or fundamental indicators as input features, predicts stock prices, ranks stocks by predicted return, and selects top performers each year with a fixed number of stocks. Portfolios are rebalanced annually using the same strategies, and performance is evaluated via compounded annual growth rate (CAGR) against benchmarks such as the S&P 500. Results are analyzed with discussion of extensions for future work.","United Arab Emirates University  \nScholarworks@UAEU  \n\n| Theses | Electronic Theses and Dissertations |\n| --- | --- |\n\n4-2025  \nCONSTRUCTION OF STOCK PORTFOLIOS BY MACHINE LEARNING METHODS  \nAlfan Gehad Abulehia  \nFollow this and additional works at: [https://scholarworks.uaeu.ac.ae/all_theses](https://scholarworks.uaeu.ac.ae/all_theses)  \n Part of the Mathematics Commons  \nMASTER THESIS NO. 2025: 17  \nCollege of Science  \nDepartment of Mathematical Sciences  \nCONSTRUCTION OF STOCK PORTFOLIOS BY MACHINE LEARNING METHODS  \nAlfan Gehad Hasan Abulehia  \nApril 2025  \nUnited Arab Emirates University College of Science  \nDepartment of Mathematical Sciences  \nCONSTRUCTION OF STOCK PORTFOLIOS BY MACHINE LEARNING METHODS  \nAlfan Gehad Hasan Abulehia  \nThis dissertation is submitted in partial fulfillment of the requirements for the degree of Master of Science in Mathematics  \nApril 2025  \nUnited Arab Emirates University Masters Thesis  \n2025: 17  \nCover: Recurrent Neural Network in both folded and unfolded forms.  \n(Photo by: Alfan Gehad Hasan Abulehia)  \n© 2025 Alfan Gehad Hasan Abulehia, Al Ain, UAE All Rights Reserved  \nPrint: University Print Service, UAEU 2025  \nDeclaration of Original Work  \nI, Alfan Gehad Hasan Abulehia, the undersigned, a graduate student at the United Arab Emirates University (UAEU), and the author of this thesis entitled “Construction of Stock Portfolios by Machine Learning Methods ”, hereby, solemnly declare that this thesis is my own original research work that has been done and prepared by me under the supervision of Dr. Ho Hon Leung, in the College of Science at UAEU. This work has not previously been presented or published, or formed the basis for the award of any academic degree, diploma or a similar title at this or any other university. Any materials borrowed from other sources (whether published or unpublished) and relied upon or included in my thesis have been properly cited and acknowledged in accordance with appropriate academic conventions. I further declare that there is no potential conflict of interest with respect to the research, data collection, authorship, presentation and/or publication of this  \nthesis.  \nStudent’s Signature  \nDate: 25 April, 2025  \nApproval of the Master Thesis  \nThis Master Thesis is approved by the following Examining Committee Members:  \n1) Advisor (Committee Chair): Ho Hon Leung  \nTitle: Associate Professor Department of Mathematical Sciences College of Science  \nUnited Arab Emirates University  \nSignature:   \nDate: 15/05/2025  \n2) Member: Youssef El Khatib  \nTitle: Professor  \nDepartment of Mathematical Sciences College of Science  \nUnited Arab Emirates University  \nSignature:   \nDate: 19/05/2025  \n3) Member (External Examiner): Kotha Kiran Kumar  \nTitle: Professor  \nDepartment of Finance and Accounting IIM Indore, India Signature:  \nDate: 19/05/2025  \nThis Masters Thesis is accepted by:  \nDean of the College of Science: Professor Maamar Benkraouda  \nSignature   Date  21 May 2025   \nDean of the College of Graduate Studies: Professor Ali Al-Marzouqi  \nDate  22/05/2025  \nAbstract  \nWe study the theory and application of two machine learning (ML) algorithms: Long-Short Term Memory Network (LSTM) and Random Forest. The study begins by providing an overview of mathematical foundation, highlighting the significance of mathematics in machine learning. We study and explain the mathematical details involved in these two algorithms. We also study closely related subjects which include but not limited to gradient descent, automatic differentiation, and recurrent neural network. The main ideas behind these topics form the foundation of any ML algorithms.  \nAs an application of the ML algorithms, we focus on the U.S. stock market. We build stock portfolios by various strategies which are primarily based on LSTM and Random Forest. This thesis can be viewed as an application of machine learning to the field of stock market analysis. The stock portfolios are constructed based on c","cbCaivzWvUIBnjQV","https://ap.wps.com/l/cbCaivzWvUIBnjQV","pdf",2711123,1,83,"English","en",105,"# Abstract\n## Machine learning foundations (LSTM, Random Forest)\n## Related methods: gradient descent and automatic differentiation\n## Application to U.S. stock market portfolios\n## Portfolio construction, prediction, ranking, and rebalancing\n## Evaluation against market benchmarks and CAGR","[{\"question\":\"Which two machine learning algorithms are used to build and analyze stock portfolios?\",\"answer\":\"The thesis studies Long-Short Term Memory Network (LSTM) and Random Forest. It explains their mathematical details and applies them to portfolio construction.\"},{\"question\":\"What inputs and steps are used to construct the stock portfolios?\",\"answer\":\"Technical indicators or fundamental indicators are used as input features for each stock. The approach predicts returns, ranks stocks by predicted return for a trading year, selects the top stocks, and rebalances annually.\"},{\"question\":\"How is portfolio performance evaluated against benchmarks?\",\"answer\":\"Performance is measured using compounded annual growth rate (CAGR). The thesis compares the constructed portfolios with market indices such as S\\u0026P 500 and analyzes whether the portfolios can outperform the benchmark over the backtesting period.\"}]","CONSTRUCTION OF STOCK PORTFOLIOS BY MACHINE LEARNING METHODS - Master Thesis 2025: 17 | PDF",1785684396,209,{"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},"construction-of-stock-portfolios-by-machine-learning-methods-master-thesis-2025-17","",{"@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/construction-of-stock-portfolios-by-machine-learning-methods-master-thesis-2025-17/118587/",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},"Which two machine learning algorithms are used to build and analyze stock portfolios?","Question",{"text":75,"@type":76},"The thesis studies Long-Short Term Memory Network (LSTM) and Random Forest. It explains their mathematical details and applies them to portfolio construction.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What inputs and steps are used to construct the stock portfolios?",{"text":80,"@type":76},"Technical indicators or fundamental indicators are used as input features for each stock. The approach predicts returns, ranks stocks by predicted return for a trading year, selects the top stocks, and rebalances annually.",{"name":82,"@type":73,"acceptedAnswer":83},"How is portfolio performance evaluated against benchmarks?",{"text":84,"@type":76},"Performance is measured using compounded annual growth rate (CAGR). The thesis compares the constructed portfolios with market indices such as S&P 500 and analyzes whether the portfolios can outperform the benchmark over the backtesting 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"]