[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118678-pt":3,"doc-seo-118678-112":30,"detail-sidebar-cat-0-pt-112":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},118678,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",32,"Pesquisa e Relatórios","Previsão da Estrutura a Termo da Taxa de Juros - Uma Abordagem com Machine Learning","Ao longo do tempo, diversos estudos buscaram prever a estrutura a termo das taxas de juros, mas ainda não há um método predominante. O trabalho propõe a utilização de modelos de machine learning aplicados a uma base de variáveis macroeconômicas. Os resultados indicam capacidade de previsão conforme esperado; no entanto, no curto prazo não há desempenho consistente superior ao Random Walk, com vantagem apenas conforme o horizonte aumenta. Pelo teste de Diebold-Mariano, não se observa evidência de superioridade, demandando novos estudos.","PREDICTING THE TERM STRUCTURE OF INTEREST RATE: A MACHINE LEARNING  \nAPPROACH*  \nPREVIS˜AO DA ESTRUTURA A TERMO DA TAXA DE JUROS: UMA ABORDAGEM COM  \nMACHINE LEARNING  \nNatanael Colrio Teixeira** Nelson Seixas dos Santos***  \nABSTRACT  \nOver time, several studies have attempted to predict the term structure of interest rates, each study has proposed a methodology for this purpose, but there is still no predominant method. In this article, we propose the use of machine learning models applied to a database of macroeconomic variables. The results show that machine learning models are capable of making predictions as expected, however, in the short term they still do not consistently outperform Random Walk, only as the horizon increases. Using the Diebold-Mariano test, it was not possible to find evidence indicating the superiority of machine learning models, and further studies are needed to advance on the subject.  \nKeywords: Machine Learning. Interest Rate. Forecasts. Term Structure.  \nRESUMO  \nAo longo do tempo, diversos estudos tentaram prever a estrutura a termo das taxas de juros, cada estudo props uma metodologia para tal, mas ainda no hum mtodo predominante. Neste artigo, propomos a utilizac¸o de modelos de machine learning aplicados a um banco de dados de variveis macroeconmicas.  \nOs resultados mostram que os modelos de machine learning so capazes de fazer previses conforme o esperado, no entanto, no curto prazo ainda no superam consistentemente o Random Walk, apenas  medida que o horizonteaumenta. Utilizando o teste de Diebold-Mariano, no foi possıvel encontrar´ evidncias que indiquem a superioridade dos modelos de machine learning, sendo necessrios mais estudos para avanc¸ar no assunto.  \nPalavras-chave: Aprendizado de Mquina. Taxa de Juros. Previso. Estruturaa Termo.  \n* Course Completion Work presented in 2024/1, to the Department of Economic Sciences and International Relations of the Faculty of Economic Sciences of the Federal University of Rio Grande do Sul (UFRGS), as a partial requirement for obtaining the title of Bachelor of Economic Sciences.  \n** Graduating in Economic Sciences from the Federal University of Rio Grande do Sul ([natasmice@icloud.com](natasmice@icloud.com) ) .  \n***Advisor. PhD in Economic Theory from the Faculty of Economics, Administration and Accounting of the University of So Paulo (FEA/USP) . Master in Economics from the Graduate School of Economics at Fundac¸o Getulio Vargas (EPGE/FGV-RJ) . Professor at the Department of Economics and International Relations at the Federal University of Rio Grande do Sul. ([nelson.seixas@ufrgs.br](nelson.seixas@ufrgs.br) ).  \n2  \n1 INTRODUCTION  \nThe term structure of the interest rate is a function that relates time and interest rates  \nas defined by (Fisher, 1930) where he introduced his expectations hypothesis theory to explain the dynamics of the term structure. This model describes how the term structure of interest rates was formed by agents’ preferences for more liquid assets and their expectation of future changes in interest rates. Investors would accept the risk of holding less liquid assets in their portfolios, as long as they could be remunerated at a higher rate in the future (liquidity premium), in such case the long-term interest rate would tend to be higher than the short-term rate. The setup of Fisher was purely deterministic though, which makes it hard to analyse the consequences of random shocks in most variables that affects the term structure.  \nOn the other hand, the general model of asset pricing available around the 1930’s, introduced by (Bachelier, 1900), have already described asset prices movement as a continuous-time stochastic process called Brownian motion. It is stated that the change value of an asset varies at each given moment and is independent of previous prices. This is the basic assertion on (Fama, 1970)’s theory of efficient markets, which states that it isnot possible to predict the future based on past informati","cbCaigoTU9nNLPaF","https://ap.wps.com/l/cbCaigoTU9nNLPaF","pdf",352201,1,20,"Portuguese","pt",112,"# Introdução\n## Hipóteses e modelos clássicos da estrutura a termo\n## Modelos estocásticos e expectativas\n## Extensões e evidências empíricas\n## Motivação para machine learning e comparação com Random Walk","[{\"question\":\"Qual é o objetivo do trabalho sobre a estrutura a termo das taxas de juros?\",\"answer\":\"Usar modelos de machine learning, treinados com variáveis macroeconômicas, para realizar previsões da estrutura a termo das taxas de juros e avaliar seu desempenho.\"},{\"question\":\"Como os modelos de machine learning se comparam ao Random Walk?\",\"answer\":\"Eles acompanham o comportamento esperado, mas no curto prazo não superam consistentemente o Random Walk; a vantagem aparece quando o horizonte de previsão aumenta.\"},{\"question\":\"O teste de Diebold-Mariano encontrou evidência de superioridade dos modelos?\",\"answer\":\"Não. O teste não forneceu evidências indicando a superioridade dos modelos de machine learning, sugerindo necessidade de pesquisas adicionais.\"}]","Previsão da Estrutura a Termo da Taxa de Juros - Uma Abordagem com Machine Learning | PDF",1785684851,31,{"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},"forecasting-the-term-structure-of-interest-rates-a-machine-learning-approach","",{"@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/pt/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/pt/document/pesquisa-e-relatórios/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/pt/document/forecasting-the-term-structure-of-interest-rates-a-machine-learning-approach/118678/",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","2026-08-08","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},"Qual é o objetivo do trabalho sobre a estrutura a termo das taxas de juros?","Question",{"text":76,"@type":77},"Usar modelos de machine learning, treinados com variáveis macroeconômicas, para realizar previsões da estrutura a termo das taxas de juros e avaliar seu desempenho.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Como os modelos de machine learning se comparam ao Random Walk?",{"text":81,"@type":77},"Eles acompanham o comportamento esperado, mas no curto prazo não superam consistentemente o Random Walk; a vantagem aparece quando o horizonte de previsão aumenta.",{"name":83,"@type":74,"acceptedAnswer":84},"O teste de Diebold-Mariano encontrou evidência de superioridade dos modelos?",{"text":85,"@type":77},"Não. O teste não forneceu evidências indicando a superioridade dos modelos de machine learning, sugerindo necessidade de pesquisas adicionais.","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},[94,99,103,107,111,115,119,121,125,128],{"id":95,"doc_module":4,"doc_module_name":46,"category_name":96,"show_sort_weight":97,"slug":98},26,"Contos e Romances",60,"story-novel",{"id":100,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":97,"slug":102},46,"Estilo de Vida","lifestyle",{"id":104,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":97,"slug":106},28,"Exames","exam",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":97,"slug":110},47,"Geral","general",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":97,"slug":114},29,"Histórias em Quadrinhos","comic",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":97,"slug":118},27,"Literatura","literature",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":97,"slug":120},"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":97,"slug":124},33,"Religião e Espiritualidade","religion-spirituality",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":97,"slug":127},"Saúde e Cuidados","healthcare",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":97,"slug":131},45,"Tecnologia","technology"]