[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119563-en":3,"doc-seo-119563-105":30,"detail-sidebar-cat-0-en-105":83},{"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":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},119563,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","SOCIAL NETWORKS IN CREDIT SCORING: A MACHINE LEARNING APPROACH","This research examines whether social network ties provide incremental predictive power for borrower default in credit scoring and improves the precision of related effects. Driven by advanced digital technologies and expanding access to non-financial behavioral big data, social network information is integrated with traditional financial records. Using machine learning on a large dataset of loan applications and defaults from a European lender, the study finds that combining social and financial data enhances default prediction. Bayesian analysis further supports the explanatory role of borrower social connections, and results offer practical XGBoost guidance.","SOCIAL NETWORKS IN CREDIT SCORING: A MACHINE LEARNING APPROACH  \nAhmad Abd Rabuh1, Mark Xu2 and Renatas Kizys3  \n1Oxford Brookes Business School, Oxford Brookes University, Oxford, UK  \n2Faculty of Business and Law, University of Portsmouth, Portsmouth, UK  \n3Southampton Business School, University of Southampton, Southampton, UK  \nABSTRACT  \nThis research examines if social network tie has an incremental predictive ability for borrower default in credit scoring and the precision of effect. With advanced digital technologies and increasing availability of non-financial behaviour big data, social network data has been explored to assess consumer credit scoring in research and practice. This research uses machine learning algorithms to analyse a large dataset (loan applications and defaults) obtained from a European lender. The results show that social network data, when working together with traditional financial data, improves predictive ability of borrowers’ default. A Bayesian Analysis confirms the explanatory evidence of social ties of borrowers. This research generates insights of machine learning power in analyzing imbalanced large dataset using ten different classifiers, and contributes to the theoretical debate on social capital theory as well as practical guidance of using XGBoost algorithm for lenders.  \nKEYWORDS  \nMachine Learning, Predictive Analytics, Social Networks, Credit Scoring, Financial Inclusion  \n1. INTRODUCTION  \nCredit scoring has been evolving in terms of objectives, sources, modelling, and techniques. Particularly, with big data accessibility and the advances in digital technologies, e.g. intelligent systems like artificial intelligence (AI) and machine learning (ML) in data analysis. Objectives of lenders vary from market penetration, profit maximisation (Thomas, 2009) to more socially financial inclusion and equality (McKillop, et al. 2007; Wei, et al. 2015). Financial inclusion requires provision of financial access to high calibre with thin financial files such as students, refugees (Redrup, 2017), new entrants to the job market or homestayers coming back to workforce, immigrants with high skills, craftsmen working with cash-in-hand and many other talents (McEvoy and Chakraborty, 2014) . For example, the Migration Observatory at the University of Oxford reported sharp increase in unemployment rates since 2020 among migrants in the UK (Fernandez-Reino & Rienzo, 2021). Finding ways to include those who cannot access credit will reduce social inequality (Wei et al., 2015) . One of the challenges, for including more borrowers, is information asymmetry, which arises when one party has limited access to information that is kept by another contracted party (Yan, et al. 2015; Ackert and Deaves, 2009) .  \nTraditional data represented ‘hard ’ information (Lin et al., 2013) and was retrieved from borrowers’financial history at the time of application (Leow and Crook, 2016) . Such data, like average balance, past credit performance in addition to demographics dominated credit scoring for quite some time, but alternative and non-traditional data including social data has been increasingly-used by innovative lenders (Lazarow, 2017) . Meanwhile, models underpinning credit scoring vary from static and parametric to dynamic and non-parametric based (Chen et al., 2018) . Machine learning models are capable of learning iteratively from training datasets to classify or predict risk level of prospectus borrowers, especially when a borrower has thin financial information and face unstable circumstances.  \nResearch into the effectiveness of non-financial data modelling and the associated techniques (ML) for credit scoring is patchy. Particularly, when referring to social network data as one of the emerging non-financial data in credit, there is a lack of precision on how social network effects credit scoring.  \nThis research aims to examine if social network data - specifically the default tie, has an incremental predict","cbCaiqtHQwvvSFgx","https://ap.wps.com/l/cbCaiqtHQwvvSFgx","pdf",1273183,1,7,"English","en",105,"# Introduction\n# Literature Review\n## Traditional Credit Scoring Models and Data\n## Social Networks and Machine Learning for Credit Scoring\n# Methodology\n## Dataset Preparation and Modeling\n# Results and Discussion\n# Conclusion and Future Research Agenda","[{\"question\":\"What do the results and Bayesian analysis indicate?\",\"answer\":\"The results show improved predictive ability for default when social data is used alongside financial data, and Bayesian analysis confirms explanatory evidence for social ties.\"}]","SOCIAL NETWORKS IN CREDIT SCORING: A MACHINE LEARNING APPROACH | PDF",1785724991,18,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"social-networks-in-credit-scoring-a-machine-learning-approach","",{"@graph":36,"@context":77},[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/social-networks-in-credit-scoring-a-machine-learning-approach/119563/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What do the results and Bayesian analysis indicate?","Question",{"text":75,"@type":76},"The results show improved predictive ability for default when social data is used alongside financial data, and Bayesian analysis confirms explanatory evidence for social ties.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]