[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122940-en":3,"doc-seo-122940-105":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},122940,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Monthly GDP nowcasting with Machine Learning and Unstructured Data","Machine Learning “nowcasting” models support faster, more informed decisions for both public and private sectors under delayed macroeconomic data releases. This study proposes ML-based GDP growth projection models for Peru’s monthly rates by combining structured macroeconomic indicators with high-frequency unstructured sentiment variables. Using data from January 2007 to May 2023, covering 91 leading indicators, the work compares six ML algorithms to select the most accurate predictors. Results show ML models with unstructured data outperform traditional AR and Dynamic Factor Models, reducing prediction errors by about 20%–25%, especially during high-uncertainty periods such as crises.","arXiv :2402 .04165v1 [ econ .EM] 6 Feb 2024  \nMonthly GDP nowcasting with Machine Learning and  \nUnstructured Data  \nJuan Tenorioa , Wilder Perezb  \na Universidad Peruana de Ciencias Aplicadas, 2390 Prolongaci´on Primavera, Santiago de  \nSurco, 15023, Lima, Peru, [pcefjten@upc.edu.pe](pcefjten@upc.edu.pe)  \nb Universidad Cient´ıfica del Sur, Panamericana Sur Km  \n19, Chorrillos, 15067, Lima, Peru  \nAbstract  \nIn the dynamic landscape of continuous change, Machine Learning (ML)“nowcasting” models offer a distinct advantage for informed decision-making in both public and private sectors. This study introduces ML-based GDP growth projection models for monthly rates in Peru, integrating structured macroeconomic indicators with high-frequency unstructured sentiment variables. Analyzing data from January 2007 to May 2023, encompassing 91 leading economic indicators, the study evaluates six ML algorithms to identify optimal predictors. Findings highlight the superior predictive capability of ML models using unstructured data, particularly Gradient Boosting Machine, LASSO, and Elastic Net, exhibiting a 20% to 25% reduction in prediction errors compared to traditional AR and Dynamic Factor Models (DFM) . This enhanced performance is attributed to better handling of data of ML models in high-uncertainty periods, such as economic crises.  \nKeywords: Real-time forecast, Machine Learning Algorithms, Big Data.  \n1. Introduction  \nMaking decisions in real-time is a true challenge for policymakers, given that the primary barrier they face is the usual delay in the availability of updated information about macroeconomic aggregates. In most cases, the economic variables show a delay of between 30-45 days on average, includingthe time for revisions and retrospectives. To address the issue of extended delays in the publication of key economic aggregates, the concept of nowcasting is proposed, which aims to predict the present, the very near future and  \nPreprint submitted to International Journal of Forecasting February 7, 2024  \nthe very recent past [1] . One of the most traditional nowcasting approaches is the Dynamic Factor Model (DFM) which is a widely used method in central banks to predict GDP [2, 3, 4, 5, 6, 7, 8] . For instance, [2] proposed a methodology to assess the marginal impact of the publication of monthlyupdated data on forecasts of quarterly-published real Gross Domestic Product (GDP) growth. The method presented by these authors was able to track the real-time flow of information that central banks monitor by handling large datasets with staggered publication dates and updating primary forecasts each time new higher-frequency data is published. Another seminal study was proposed by [9] where they do real-time estimations of the current state of the US economy. This approach included data complexity and provided useful information about the relationship between macroeconomics and asset prices.  \nA critical challenge to that traditional approach is the increase in uncertainty in the estimates which use a limited set of variables, and often fall short. Nevertheless, the continuous stride forward in the new generation of high-frequency data has changed how prediction models face the uncertainty inherent in this information. As a result, in the recent few years, both central banks and international institutions have adopted methodological focuses that incorporate machine learning, and take advantage of the abundant quantity of data that come from search engines and social media such as [10], [11] and [8] . Those methods provide more accurate predictions by incorporating various variables and new sources of unstructured data. As described [12], these techniques are divided into two main brands, supervised and unsupervised ML. [12] explains that unsupervised MLs are looking for groups of observations that are similar in terms of their covariance. Thus, a“dimensionality reduction” can be performed. Unsupervised MLs commonly use videos,","cbCaim4n1FBaba0q","https://ap.wps.com/l/cbCaim4n1FBaba0q","pdf",899435,1,29,"English","en",105,"# Introduction\n## Nowcasting and data-release delays\n## Dynamic Factor Models as a baseline\n## Role of machine learning and unstructured data\n## Supervised vs. unsupervised approaches","[{\"question\":\"Why do policymakers use nowcasting models for GDP?\",\"answer\":\"Nowcasting addresses the delay in updated macroeconomic aggregates, typically requiring 30–45 days due to revisions and retrospectives.\"},{\"question\":\"How does this study combine structured and unstructured data?\",\"answer\":\"It integrates 91 leading macroeconomic indicators with high-frequency unstructured sentiment variables to improve monthly GDP growth projections.\"},{\"question\":\"Which ML approaches show the strongest predictive performance and when?\",\"answer\":\"The study finds ML models using unstructured data—especially Gradient Boosting Machine, LASSO, and Elastic Net—reduce prediction errors by about 20%–25%, with clear benefits in high-uncertainty periods such as economic crises.\"}]","Monthly GDP nowcasting with Machine Learning and Unstructured Data | PDF",1785813795,73,{"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},"monthly-gdp-nowcasting-with-machine-learning-and-unstructured-data","",{"@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/monthly-gdp-nowcasting-with-machine-learning-and-unstructured-data/122940/",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","2026-08-04",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},"Why do policymakers use nowcasting models for GDP?","Question",{"text":75,"@type":76},"Nowcasting addresses the delay in updated macroeconomic aggregates, typically requiring 30–45 days due to revisions and retrospectives.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does this study combine structured and unstructured data?",{"text":80,"@type":76},"It integrates 91 leading macroeconomic indicators with high-frequency unstructured sentiment variables to improve monthly GDP growth projections.",{"name":82,"@type":73,"acceptedAnswer":83},"Which ML approaches show the strongest predictive performance and when?",{"text":84,"@type":76},"The study finds ML models using unstructured data—especially Gradient Boosting Machine, LASSO, and Elastic Net—reduce prediction errors by about 20%–25%, with clear benefits in high-uncertainty periods such as economic crises.","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"]