[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116904-en":3,"doc-seo-116904-105":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},116904,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Equity Sector Rebalancing via Machine Learning","This dissertation examines whether supervised machine learning models—Artificial Neural Networks, Support Vector Machines, and Logistic Regressions—can predict sector-level shifts in equity returns. It addresses limits of traditional linear factor models by incorporating a wider set of predictors that capture effects driven by hard-to-forecast events. Models forecast whether each sector’s one-month excess return is positive or negative, then allocate capital across sectors and treasury bonds to build equal- and value-weighted portfolios. Backtesting over 25 years against the S&P500 shows improved absolute and risk-adjusted returns, with stronger protection during larger market declines.","Equity Sector Rebalancing via Machine Learning  \nTiago Ramos  \nDissertation written under the supervision of professor Dan Tran  \nDissertation submitted in partial fulfilment of requirements for the MSc in Finance, at the Universidade Católica Portuguesa, 03/01/2023 .  \nAbstract  \nIn this dissertation the author will analyze whether supervised machine learning models namely Artificial Neural Networks, Support Vector Machines and Logistic Regressions can predict shiftsin equity returns on a sector basis. Typically, in asset pricing linear factor models with a small number of variables are used. However, due to market efficiency, equity returns are highly influenced by unforecastable events making this task more challenging. Simple linear regressions also have difficulty incorporating a larger number of predictor variables, which the literature has accumulated over the decades, creating an opportunity for machine learning techniques.  \nThe Machine Learning models will be used to forecast whether the excess return of each equity sector over a period of one month will be positive or negative. Then using the model’s predictions capital will be allocated between the sectors and treasury bonds, building different portfolios namely an equal weighted, a value weighted portfolio. After all portfolios are built their performance will then be compared against the benchmark, namely the S&P500 index being back tested over a period of 25 years.  \nThe portfolios built using the forecasts from the ML models lead to an increase in absolute and risk adjusted returns beating the benchmark. The implemented strategies were shown to protect investors against larger market declines, showing the potential of Machine Learning as an investment tool.  \nTittle: Equity Sector Rebalancing via Machine Learning  \nAuthor: Tiago Coutinho Ramos  \nKeywords: Sector Allocation, Market Timing, Machine Learning, Logistic Regressions, Support Vector Machines, Neural Networks  \nResumo  \nNesta dissertação o autor vai analisar se os modelos de machine learning nomeadamente Redes Neurais Artificiais, Máquina de Vetores de Suporte e Regressões Logísticas , conseguem prever mudanças nos retornos dos vários setores de mercado. Tipicamente, na definição do preço de ativos, são usados modelos de fatores lineares com um pequeno número de variáveis. Contudo, devido á eficiência do mercado, os retornos de ações são influenciados por eventos imprevisíveis aumentando a complexidade do problema. As regressões lineares simples têm dificuldade emincorporar um número vasto de variáveis, que a literatura Financeira veio a acumular ao longo das décadas, criando uma oportunidade para técnicas de machine learning.  \nOs modelos de Machine Learning serão utilizados para realizar previsões sobre se o retorno de excesso sobre o período de um mês será positivo ou negativo. Utilizando as previsões dos modelos , o capital será alocado entre os vários setores do mercado e obrigações de tesouraria, construindo diferentes portfolios. Estando os portfolios construídos a respetiva performance será avaliada ecomparada contra o benchmark, nomeadamente o índice do S&P500, durante um período de 25 anos.  \nOs portfolios contruídos usando as previsões dos modelos de ML levaram a um aumento de retornos absolutos e ajustados ao risco batendo o benchmark. As estratégias teriam protegido investidores contra quedas acentuadas do mercado, mostrando o potencial de Machine Learning como ferramenta de investimento.  \nTítulo: Rebalanceamento de Setores de Investimento através de Machine Learning  \nAutor: Tiago Coutinho Ramos  \nPalavras Chave: Alocação por Setor, Timing de Mercado, Machine Learning, Regressão Logística, Máquina de Vetores de Suporte, Redes Neurais Artificiais  \nTable of Contents  \n1. Introduction………………………………………………………………………………1  \n2. Literature Review………………………………………………………………………...3  \n3. Data………………………………………………………………………………………. 7  \n3.1. Fundamental Features…………………………………………………………………7  \n3.2. Macroeconomic Fe","cbCaisuQD15C1hx5","https://ap.wps.com/l/cbCaisuQD15C1hx5","pdf",889654,1,48,"English","en",105,"# Introduction\n# Literature Review\n# Data\n## Fundamental Features\n## Macroeconomic Features\n## Technical Features\n## Market Sentiment Features\n## Data Analysis\n# Methodology\n## Data Preprocessing\n## Training and Testing Sets\n## Tuning Hyperparameters\n## Logistic Regression\n## Support vector Machines (SVM)\n## Artificial Neural Networks\n## Portfolio Construction\n# Results\n## Model Performance\n## Feature Importance\n## Portfolio Performance\n# Conclusion\n# Bibliography\n# Appendix","[{\"question\":\"Which machine learning models are used to predict sector return shifts?\",\"answer\":\"The dissertation uses supervised models including Artificial Neural Networks, Support Vector Machines, and Logistic Regressions to predict whether sector excess returns will be positive or negative over a one-month horizon.\"},{\"question\":\"How are the portfolio allocations constructed from the machine learning predictions?\",\"answer\":\"Model forecasts determine capital allocation between equity sectors and treasury bonds. The study builds different portfolios, including equal-weighted and value-weighted portfolios.\"},{\"question\":\"What benchmark and evaluation period are used to test performance?\",\"answer\":\"Portfolio performance is compared against the S\\u0026P 500 index using a backtest over a 25-year period.\"}]","Equity Sector Rebalancing via Machine Learning | PDF",1785672392,121,{"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},"equity-sector-rebalancing-via-machine-learning","",{"@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/equity-sector-rebalancing-via-machine-learning/116904/",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 machine learning models are used to predict sector return shifts?","Question",{"text":75,"@type":76},"The dissertation uses supervised models including Artificial Neural Networks, Support Vector Machines, and Logistic Regressions to predict whether sector excess returns will be positive or negative over a one-month horizon.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the portfolio allocations constructed from the machine learning predictions?",{"text":80,"@type":76},"Model forecasts determine capital allocation between equity sectors and treasury bonds. The study builds different portfolios, including equal-weighted and value-weighted portfolios.",{"name":82,"@type":73,"acceptedAnswer":83},"What benchmark and evaluation period are used to test performance?",{"text":84,"@type":76},"Portfolio performance is compared against the S&P 500 index using a backtest over a 25-year 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"]