[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120915-en":3,"doc-seo-120915-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},120915,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","A Machine Learning approach to constructing weekly GDP tracker using Google Trends - Research","The COVID-19 pandemic exposed the limitations of traditional indicators when timely, granular information is critical for policy decisions. This study constructs the first Weekly Growth Domestic Product (GDP) Tracker in the Philippines by combining topic- and category-based Google Trends search volumes with machine learning models. The results show the tracker is a high-frequency tool for nowcasting economic activity, achieving lower root mean square error (RMSE) than benchmark autoregression models on both training and testing datasets.","5th International Conference on Advanced Research Methods and Analytics (CARMA2023)  \nUniversidad de Sevilla, Sevilla, 2023  \nDOI: [http://dx.doi.org/10.4995/CARMA2023.2023.16039](http://dx.doi.org/10.4995/CARMA2023.2023.16039)  \nA Machine Learning approach to constructing weekly GDP tracker using Google Trends  \nJean Christine A. Armas1, Cherrie R. Mapa1, Ma. Ellysah Joy T. Guliman1, Michael Lawrence G. Castañares1, Genna Paola S. Centeno1  \n1Department of Economic Research, Bangko Sentral ng Pilipinas, Philippines  \nAbstract  \nThe outbreak of the COVID-19 pandemic further highlighted the limitation of existing traditional indicators as policy formulation, particularly during crisis periods, demands timely and granular data. We construct the first Weekly Growth Domestic Product (GDP) Tracker in the Philippines using topic-and category- based Google Trends search volumes with the aid of machine learning models. We find that our Weekly GDP Tracker is a useful highfrequency tool in nowcasting economic activity. We also show that the machine learning-based GDP tracker outperforms the traditional autoregression models under study in terms of lower root mean square error (RMSE) for both train and test datasets. On the whole, our Weekly GDP Tracker can serve as a useful complementary surveillance tool for monitoring economic activity.  \nKeywords: Nowcasting; GDP; Google Trends; machine learning models; neural networks.  \nThis work is licensed under a Creative Commons License CC BY-NC-SA 4.0  \nEditorial Universitat Politcnica de Valncia 55  \n1. Introduction  \nTimely and accurate information are essential inputs for policy formulation. Data becomeseven more important during crisis periods, such as the COVID-19 pandemic, as high frequency and granular data are integral in crafting prompt and appropriate policy responses that can help attenuate the impact of a crisis. However, official economic statistics are typically published with a significant time lag. In the case of the COVID-19 pandemic, an extra layer of challenge emerged as collection of official statistics was hampered by the imposition of mobility restrictions during the height of the health crisis. These motivate the interest of policymakers, including monetary authorities, to tap alternative data sources to supplement existing official statistics or traditional indicators.  \nIn the area of macroeconomic surveillance, the Gross Domestic Product (GDP) is the official and most comprehensive indicator for measuring economic activity. In the Philippines, the GDP is available on a quarterly basis and is published by the Philippine Statistics Authority (PSA) 40 days after the reference quarter except for the Q4 GDP which is released after 30 days.1 Due to this publication lag, the Bangko Sentral ng Pilipinas (BSP) uses a number of models to nowcast the GDP as information on the output growth and the cyclical position of the economy in the business cycle are important considerations in policy formulation. Thus far, the BSP’s nowcasting models for the GDP have employed traditional statistics with nowcast updates implemented on a monthly or quarterly basis.  \nThis study attempts to build a high-frequency indicator of GDP growth that capitalizes on the use of alternative data. Our objectives are: (a) to construct a weekly GDP Tracker that can nowcast quarterly GDP growth using machine learning models trained on pre-identified Google search volumes; and (b) to evaluate the usefulness of Google Trends data in nowcasting GDP pending the availability of official statistics. To ensure that the use of Google Trends data is suitable for statistical and economic analysis, the topic-and categorybased searches are selected based on the authors’ expert and sensible judgment on mapping relevant internet searches with the components of National Accounts of the Philippines (NAP) . To the authors’ knowledge, this is the first empirical research in the Philippines to use both the topic-and category-b","cbCail3MWJT4oYUK","https://ap.wps.com/l/cbCail3MWJT4oYUK","pdf",472557,1,"English","en",105,"# Introduction\n## Data: Google Trends Data Selection and Statistical Pre-processing\n### Google Trends Selection","[{\"question\":\"Why is a weekly GDP tracker needed in policy making?\",\"answer\":\"Official GDP statistics are released with a significant time lag, which limits responsiveness during crises. A high-frequency tracker supports faster, more appropriate policy responses.\"},{\"question\":\"How does the study construct the Weekly GDP Tracker?\",\"answer\":\"It uses topic- and category-based Google Trends search volumes and trains machine learning models to nowcast quarterly GDP growth using weekly signals.\"},{\"question\":\"How does the machine learning tracker perform versus traditional models?\",\"answer\":\"The machine learning-based tracker outperforms the autoregression models, delivering lower root mean square error (RMSE) on both training and test datasets.\"}]","A Machine Learning approach to constructing weekly GDP tracker using Google Trends - Research | PDF",1785732661,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"a-machine-learning-approach-to-constructing-weekly-gdp-tracker-using-google-trends-research","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/a-machine-learning-approach-to-constructing-weekly-gdp-tracker-using-google-trends-research/120915/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is a weekly GDP tracker needed in policy making?","Question",{"text":74,"@type":75},"Official GDP statistics are released with a significant time lag, which limits responsiveness during crises. A high-frequency tracker supports faster, more appropriate policy responses.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the study construct the Weekly GDP Tracker?",{"text":79,"@type":75},"It uses topic- and category-based Google Trends search volumes and trains machine learning models to nowcast quarterly GDP growth using weekly signals.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the machine learning tracker perform versus traditional models?",{"text":83,"@type":75},"The machine learning-based tracker outperforms the autoregression models, delivering lower root mean square error (RMSE) on both training and test datasets.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]