[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128375-en":3,"doc-seo-128375-105":31,"detail-sidebar-cat-0-en-105":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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128375,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Essays in Econometrics and Machine Learning - Thesis (Ph.D. in Economics)","Doctoral thesis examining high-frequency inflation expectations using big data, combining newspaper text, Twitter/X data, Google search volume, and consumer survey inflation expectations. Focuses on text-based methodology, including raw text preprocessing, large language model binary classification, detection of future price dynamics sentences, and tense aggregation to build directional indicators. Evaluates results by benchmarking granular textual expectations against hard data, including news and social media expectations and co-movement between actual inflation and media signals.","Université de Montréal  \nEssays in Econometrics and Machine Learning  \nPar  \nGbètoho Firmin AYIVODJI  \nDépartement de sciences économiques Faculté des arts et sciences  \nThèse présentée à la Faculté des études supérieuresen vue de l’obtention du grade de Philosophiæ Doctor (Ph.D.)  \nen sciences économiques  \nAugust, 2025  \n©Gbètoho Firmin AYIVODJI, 2025  \nUniversité de Montréal  \nFaculté des Études Supérieures et Postdoctorales  \nCette thèse intitulée :  \nEssays in Econometrics and Machine Learning  \nPar  \nGbètoho Firmin AYIVODJI  \na été évaluée par un jury composé des personnes suivantes :  \nRené Garcia, président du jury  \nMarine Carrasco, membre du jury Benoit Perron, directeur de recherche Patrick Richard, examinateur externe  \nThèse déposée August, 2025  \nÀ ma bien aimée Robertina, mes parents Rebecca et Joseph, mon feu père Gabriel, aussi à  \nmes frères et sœurs  \nREMERCIEMENTS  \nACKNOWLEDGEMENTS  \nJe tiens tout d’abord à exprimer ma profonde gratitude envers mon directeur de recherche, Benoit Perron, qui a accepté de m’encadrer et me guider dans cette thèse de doctorat. Je lui suis infiniment reconnaissant pour sa confiance, sa foi en mes capacités, son inlassable disponibilité, sa gentillesse, ses précieux conseils, son soutien indéfectibleet surtout sa rigueur.  \nJe remercie également Marine Carrasco et Christopher Rauh pour leur soutien, leur confiance, leur rigueur, leur disponibilité et nos nombreuses discussions, qui m’ont permis de bénéficier de leurs conseils avisés et de leur riche expérience. Je tiens aussi à remercier René Garcia, qui a accepté de faire partie de mon comité de thèse dès madeuxième année.  \nMes remerciements vont également à Antoine Djogbenou, Prosper Dovonon, Ismael Mourifie, Karim Chalak, Dalibor Stevanovic, Kevin Moran, Philippe Goulet Coulombe, Nicolas Vincent, Jean-François Rouillard, Amine Ouazad, et Yang Zhang pour leurdisponibilité et leur générosité .  \nJe suis reconnaissant envers Patrick Richard pour avoir spontanément accepté d’examiner cette thèse. Je souhaite aussi remercier l’ensemble du corps professoral du département des sciences économiques de l’Université de Montréal pour leurenseignement et leur soutien, en particulier Lars Ehlers, Mathieu Marcoux, Guillaume Sublet, Sean Horan, Vasia Panousi, Emanuela Cardia, Immo Schott et Baris Kaymak. Merci également à l’ensemble du personnel administratif du département de sciences économiques et du Centre interuniversitaire de recherche en économie quantitative (CIREQ) .  \nPar ailleurs, je tiens à exprimer ma gratitude pour le soutien financier du gouvernement du Québec, à travers une bourse du Fonds de recherche du Québec société et culture (FRQSC), ainsi que pour le soutien ponctuel de la Chaire en macroéconomie et prévisions de l’ESG UQAM. Cette thèse a été aussi réalisée grâce à l’appui financier dudépartement et du CIREQ.  \nJe tiens également à remercier mes collègues de promotion, Marius Adom, Lucien Chaffa, et Narcisse Sandwidi, qui ont été d’une aide précieuse tout au long de cette thèse. Je remercie particulièrement mes amis Ismaël Assani, Ghislain Afavi, Juste Djabakou, Kodjo Koudakpo, Aristide Houndetoungan, Abdoul Maoude, Siwe Guy Leonel, Marlène Koffi, Stéphane N’dri, Felicien Goudou, Akim Al-mouksit, Joseph Agossa, Robert  \nDjogbenou, Idriss Tsafack, Solo Zerbo, Marius Pondi, Samuel Gingras, Jessica Kpatinde, Romel Degboe, Farell Waji, Siriac Seboka, Samiratou Kora, Bruno Monsia, Fansa Koneet Eugène Dettaa pour leur présence enrichissante au cours de ces années.  \nMes pensées et ma reconnaissance vont particulièrement à mes parents, Rebecca et Joseph, ainsi qu’à mes frères et sœurs, pour leur soutien moral inlassable et inconditionnel. Je suis particulièrement redevable à Robertina, Hannah et Joseph, sans oublier Nestor Mignanwande.  \nÀ mon second père et mentor, Gabriel Kougblenou, qui nous a quittés quelques jours seulement avant le dépôt de cette thèse, je rends un hommage vibrant. Sa rigueur, son attention et son sou","cbCailkgx3U2SAYL","https://ap.wps.com/l/cbCailkgx3U2SAYL","pdf",8289745,4,1,200,"English","en",105,"# High-Frequency Inflation Expectations from Big Data\n## Introduction\n## Data sources\n### Newspaper text\n### Twitter/X data: keywords and initial dataset\n### Google search volume data\n### Consumer Survey Inflation Expectations Data\n## Methodology: text-based inflation expectations\n### Raw text preprocessing\n### Inflation text binary classification using Large Language Models\n### Detecting future price dynamics sentences\n### Tense Aggregation\n### Computation of aggregate directional indicators\n## Benchmarking granular textual expectations against hard data\n### News-based inflation expectations\n### Twitter-based inflation expectations\n### Comovement between actual inflation and media expectations","[{\"question\":\"What data sources are used to study inflation expectations at high frequency?\",\"answer\":\"The thesis uses newspaper text, Twitter/X data, Google search volume data, and consumer survey inflation expectations data.\"},{\"question\":\"How are text-based inflation expectations constructed using machine learning?\",\"answer\":\"The approach includes raw text preprocessing, large language model-based binary classification of inflation text, detection of future price dynamics sentences, tense aggregation, and computation of aggregate directional indicators.\"},{\"question\":\"How are the text-based expectations validated against real-world outcomes?\",\"answer\":\"Results are benchmarked against hard data by comparing granular textual expectations from news and Twitter with actual inflation and assessing their co-movement.\"}]","Essays in Econometrics and Machine Learning - Thesis (Ph.D. in Economics) | PDF",1785947161,504,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"essays-in-econometrics-and-machine-learning-thesis-phd-in-economics","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/essays-in-econometrics-and-machine-learning-thesis-phd-in-economics/128375/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",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},"What data sources are used to study inflation expectations at high frequency?","Question",{"text":76,"@type":77},"The thesis uses newspaper text, Twitter/X data, Google search volume data, and consumer survey inflation expectations data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are text-based inflation expectations constructed using machine learning?",{"text":81,"@type":77},"The approach includes raw text preprocessing, large language model-based binary classification of inflation text, detection of future price dynamics sentences, tense aggregation, and computation of aggregate directional indicators.",{"name":83,"@type":74,"acceptedAnswer":84},"How are the text-based expectations validated against real-world outcomes?",{"text":85,"@type":77},"Results are benchmarked against hard data by comparing granular textual expectations from news and Twitter with actual inflation and assessing their co-movement.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]