[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123274-en":3,"doc-seo-123274-105":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},123274,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Predicting policy funding allocation with Machine Learning - A case study","Allocating funds through competitive opportunities is a core tool of place-based development policies, capable of generating economic benefits and revitalising “left-behind” territories. Using Machine Learning (ML), the paper examines whether actors expected to benefit from EU development funding (2014–2020) in Italy can be predicted. Eight ML classification algorithms are tested, and Random Forest, Extreme Gradient Boosting, and Support Vector Machine prove most predictive. The study enables out-of-sample forecasts and identifies drivers such as territorial attributes, economic dimensions, and production specialisation, supporting tailored public policies for green transition.","Socio-Economic Planning Sciences 98 (2025) 102175  \n| Predicting policy funding allocation with Machine Learning Nicola Caravaggio a,∗, Giuliano Resce a, Cristina Vaquero-Piñeirob\u003Cbr>a Department of Economics, University of Molise, Italy\u003Cbr>b Department of Economics and Rossi-Doria Center, Roma Tre University, Italy |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| JEL classification: H7\u003Cbr>O2\u003Cbr>Q01\u003Cbr>Keywords:\u003Cbr>Competitive funding Sustainable development Machine learning Firm-level data\u003Cbr>Public policies |  | Allocating funds through competitive opportunities is a core tool of place-based development policies, as it can generate economic benefits and support the revitalisation of ‘left-behind’ territories. By relying on Machine Learning (ML) techniques, this paper investigates the predictability of actors expected to benefit from EU development funding over the 2014–2020 period in Italy. We implemented eight different ML classification algorithms and Random Forest, followed by Extreme Gradient Boosting, and Support Vector Machine emerged as the most predictive. The results show that it is possible to make out-of-sample predictions and diagnose the precise factors influencing fund allocation, such as territorial attributes, economic dimensions, and production specialisation. Knowing in advance potential winners of the calls can help design tailored territorial, and even sectorial, public policies to address the obstacles to local development and green transition, and to efficiently distribute resources within the policy framework. This evidence contributes to the reflection launched by the Commission on the future of the competitiveness of the EU. |\n\n1. Introduction  \nSocioeconomic and environmental challenges have strengthened the case for sustainable territorial development to play a more central role within the European Union (EU), especially in rural and inner areas [1]. Governments have implemented several place-based and community-led interventions at both national and international levels to support sustainable development. Most of these rely on competitive funding opportunities, for which local actors, such as firms, are required to participate in calls for proposals. The EU’s Resilience and Recovery Facility (RRF), in addition to the Cohesion Policy (CP) and the Rural Development Policy (RDP), have consensually emphasised the important role expected to be played by place-based interventions managed through competition procedures. For instance, a large portion of the funds from the NextGenerationEU is allocated through a direct management model, implemented by the European Commission (EC), by launching calls for proposals.1  \nThe economic literature provides extensive evidence for the effect of place-based policies [2], albeit with some caution about the difficulty  \nof achieving an efficient allocation of funds, especially in settings with structural and institutional weaknesses [3]. Nevertheless, in the literature, there is limited evidence related to the factors that may influence such allocations, and the effective interrelations and coordination among different funds, with most research in this area focusing on ex-post analyses of causal effects [4,5]. Even without examining the data, there are, in fact, good reasons to expect that some characteristics favour the likelihood of obtaining funds.  \nThe general objective of this work is to explore the validity of using data to generate informational value for policy design. Specifically, the paper aims to implement a procedure for optimising policies based on competitive fund allocation by predicting the factors that determine the likelihood of being potential winners in such calls. It also demonstrateshow this approach can be applied to a real EU place-sensitive policy for sustainable development that relies on competitive participation. Furthermore, the study provides insights into the interpretation of results, with a focus on how pa","cbCaijJEE3flezGo","https://ap.wps.com/l/cbCaijJEE3flezGo","pdf",2895056,1,16,"English","en",105,"# Introduction\n## Objective and approach\n## Competitive funding and policy context\n## Analysis and case study framework","[{\"question\":\"What is the main objective of this study?\",\"answer\":\"To test whether data can provide informational value for policy design by predicting factors that determine potential winners in competitive funding calls.\"},{\"question\":\"Which machine learning methods are identified as most predictive?\",\"answer\":\"Random Forest, Extreme Gradient Boosting, and Support Vector Machine are reported as the most predictive among the tested classification algorithms.\"},{\"question\":\"What types of factors influence policy fund allocation according to the results?\",\"answer\":\"Territorial attributes, economic dimensions, and production specialisation are highlighted as key factors affecting fund allocation outcomes.\"}]","Predicting policy funding allocation with Machine Learning - A case study | PDF",1785815647,40,{"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},"predicting-policy-funding-allocation-with-machine-learning-a-case-study","",{"@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/predicting-policy-funding-allocation-with-machine-learning-a-case-study/123274/",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},"What is the main objective of this study?","Question",{"text":75,"@type":76},"To test whether data can provide informational value for policy design by predicting factors that determine potential winners in competitive funding calls.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning methods are identified as most predictive?",{"text":80,"@type":76},"Random Forest, Extreme Gradient Boosting, and Support Vector Machine are reported as the most predictive among the tested classification algorithms.",{"name":82,"@type":73,"acceptedAnswer":83},"What types of factors influence policy fund allocation according to the results?",{"text":84,"@type":76},"Territorial attributes, economic dimensions, and production specialisation are highlighted as key factors affecting fund allocation outcomes.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]