[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119306-en":3,"doc-seo-119306-105":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},119306,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Policy evaluation and machine learning in international economics - dissertation","This dissertation investigates how machine learning can improve policy evaluation in international economics, focusing on exporter identification, treatment effect heterogeneity, and learning-by-exporting dynamics. It develops predictive models to forecast exporting status and exporter scores, then applies causal machine learning to assess the heterogeneous impact of the EU-Canada agreement. Finally, it estimates a dose-response function capturing how learning-by-exporting varies with exposure intensity, reporting results alongside robustness, sensitivity, and interpretability analyses for policy-relevant guidance.","IMT School for Advanced Studies, Lucca  \nLucca, Italy  \nPolicy evaluation and machine learning in international  \neconomics  \nPhD Program in Systems Science Track in Economics, Networks and Business Analytics  \nXXXV Cycle  \nBy  \nFrancesca Micocci  \n2025  \nThe dissertation of Francesca Micocci is approved.  \nPhD Program Coordinator: Ennio Bilancini, IMT School for Advanced Studies Lucca  \nAdvisor: Prof. Armando Rungi, IMT School for Advanced Studies Lucca  \nThe dissertation of Francesca Micocci has been reviewed by:  \nGabor Bks, Central European University, KRTK Institute of Economics and CEPR  \nGiovanna D’Inverno, Universit di Pisa  \nDaniela Maggioni, Universit Cattolica di Milano  \nIMT School for Advanced Studies Lucca  \n2025  \nTo my family and friends. This thesis is as much yours as it is mine.  \nContents  \nList of Figures x  \nList of Tables xiii  \nAcknowledgements xvi  \nVita and Publications xviii  \nAbstract xxi  \nIntroduction 1  \n1 Predicting Exporters with Machine Learning 10  \n1.1 Introduction ........................... 10  \n1.2 Related literature ........................ 14  \n1.3 Data ................................ 18  \n1.4 The empirical strategy ..................... 19  \n1.4.1 Methods ......................... 20  \n1.4.2 Predictors ........................ 25  \n1.5 Results .............................. 27  \n1.5.1 Models’ horse race ................... 27  \n1.5.2 Predictions ........................ 29  \n1.6 Robustness checks ....................... 30  \n1.7 Sensitivity to temporary trade ................. 34  \n1.8 Interpretability of predictors .................. 36  \n1.9 Internal vs. external validity .................. 41  \n1.10 How to use exporting scores .................. 43  \n1.11 Conclusions ........................... 46  \n2 The heterogeneous impact of the EU-Canada agreement with causal machine learning 48  \n2.1 Introduction ........................... 49  \n2.2 Related Literature ........................ 55  \n2.3 Data and preliminary evidence ................ 57  \n2.3.1 Customs data and trade regime changes ....... 57  \n2.3.2 Preliminary evidence .................. 60  \n2.4 Empirical strategy ........................ 64  \n2.4.1 Treated products and treated firms .......... 64  \n2.4.2 Matrix completion ................... 66  \n2.5 Results .............................. 70  \n2.5.1 Product-level analysis ................. 71  \n2.5.2 Firm-Level Analysis .................. 83  \n2.5.3 General equilibrium trade impacts .......... 89  \n2.6 Robustness and sensitivity checks .............. 90  \n2.7 Conclusions ........................... 93  \n3 A dose-response function for learning-by-exporting 95  \n3.1 Introduction ........................... 95  \n3.2 Literature Review ........................ 98  \n3.3 Data and descriptive statistics ................. 99  \n3.4 Empirical strategy ........................ 103  \n3.5 Results .............................. 107  \n3.5.1 The low-productivity trap ............... 112  \n3.5.2 Economies of scale and capital adjustment ..... 114  \n3.6 Robustness and Sensitivity ................... 117  \n3.6.1 Analysis of the Common support .......... 121  \n3.6.2 Alternative specifications ............... 125  \n3.6.3 Heterogeneity across technological trajectories ... 127  \n3.7 Conclusions and policy implications ............. 133  \nConclusions 136  \nA Supplementary materials for Chapter 1 142  \nB Supplementary materials for Chapter 2 159  \nC Supplementary materials for Chapter 3 171  \nList of Figures  \n1 Visual intuition of an exporting score............. 20  \n2 Correlation matrix of predictors ................ 26  \n3 Distributions of exporting scores of non-exporters after BARTMIA ................................ 30  \n4 Variable inclusion proportions after BART-MIA ....... 39  \n5 Premia on relevant firm dimensions across exporting scores 45  \n6 Products’ coverage in 2016 ................... 59  \n7 Firms’ coverage in 2016 ..................... 60  \n8 Time trends at the product level, intensi","cbCaiaLmlp3gFpE0","https://ap.wps.com/l/cbCaiaLmlp3gFpE0","pdf",8388685,1,229,"English","en",105,"# Introduction\n# Predicting Exporters with Machine Learning\n## Introduction\n## Related literature\n## Data\n## The empirical strategy\n## Results\n## Robustness checks\n## Sensitivity to temporary trade\n## Interpretability of predictors\n## Internal vs. external validity\n## How to use exporting scores\n## Conclusions\n# The heterogeneous impact of the EU-Canada agreement with causal machine learning\n## Introduction\n## Related Literature\n## Data and preliminary evidence\n## Empirical strategy\n## Results\n## Robustness and sensitivity checks\n## Conclusions\n# A dose-response function for learning-by-exporting\n## Introduction\n## Literature Review\n## Data and descriptive statistics\n## Empirical strategy\n## Results\n## Robustness and Sensitivity\n## Conclusions\n# Conclusions","[{\"question\":\"How does the dissertation use machine learning to predict exporters?\",\"answer\":\"It builds models and predictive features to generate exporting scores and evaluate prediction performance through model comparison, then validates results with robustness and sensitivity checks.\"},{\"question\":\"What is the role of causal machine learning in the EU-Canada agreement analysis?\",\"answer\":\"The study uses causal machine learning methods to estimate heterogeneous treatment effects, combining a structured empirical design with matrix completion and product- and firm-level analyses.\"},{\"question\":\"What does the dose-response function for learning-by-exporting measure?\",\"answer\":\"It quantifies how learning-by-exporting outcomes change as exposure intensity varies, highlighting mechanisms such as low-productivity traps and effects related to economies of scale and capital adjustment.\"}]","Policy evaluation and machine learning in international economics - dissertation | PDF",1785723631,577,{"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},"policy-evaluation-and-machine-learning-in-international-economics-dissertation","",{"@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/policy-evaluation-and-machine-learning-in-international-economics-dissertation/119306/",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","2026-08-03",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},"How does the dissertation use machine learning to predict exporters?","Question",{"text":75,"@type":76},"It builds models and predictive features to generate exporting scores and evaluate prediction performance through model comparison, then validates results with robustness and sensitivity checks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the role of causal machine learning in the EU-Canada agreement analysis?",{"text":80,"@type":76},"The study uses causal machine learning methods to estimate heterogeneous treatment effects, combining a structured empirical design with matrix completion and product- and firm-level analyses.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the dose-response function for learning-by-exporting measure?",{"text":84,"@type":76},"It quantifies how learning-by-exporting outcomes change as exposure intensity varies, highlighting mechanisms such as low-productivity traps and effects related to economies of scale and capital adjustment.","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"]