{"id":"https://openalex.org/W7150781595","doi":"https://doi.org/10.48550/arxiv.2604.02832","title":"Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spaces","display_name":"Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spaces","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7150781595","doi":"https://doi.org/10.48550/arxiv.2604.02832"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.02832","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02832","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.02832","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056487636","display_name":"Christopher Gerling","orcid":"https://orcid.org/0000-0002-7579-0751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerling, Christopher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133046619","display_name":"Hanqiu Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Hanqiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133022356","display_name":"Ying Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133063411","display_name":"Stefan Lessmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lessmann, Stefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11496","display_name":"Credit Risk and Financial Regulations","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/loan","display_name":"Loan","score":0.5911999940872192},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5831999778747559},{"id":"https://openalex.org/keywords/covariate","display_name":"Covariate","score":0.5196999907493591},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5101000070571899},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/credit-risk","display_name":"Credit risk","score":0.49219998717308044},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.37209999561309814},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.362199991941452},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3499999940395355},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.3346000015735626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200999855995178},{"id":"https://openalex.org/C2777764128","wikidata":"https://www.wikidata.org/wiki/Q189539","display_name":"Loan","level":2,"score":0.5911999940872192},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C178350159","wikidata":"https://www.wikidata.org/wiki/Q162714","display_name":"Credit risk","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4851999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43869999051094055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4027999937534332},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C2864544","wikidata":"https://www.wikidata.org/wiki/Q2914988","display_name":"Capital requirement","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C2779806880","wikidata":"https://www.wikidata.org/wiki/Q778470","display_name":"Probability of default","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C138142054","wikidata":"https://www.wikidata.org/wiki/Q5035692","display_name":"Capital allocation line","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2780759654","wikidata":"https://www.wikidata.org/wiki/Q809934","display_name":"Basel II","level":4,"score":0.2565000057220459},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C122282355","wikidata":"https://www.wikidata.org/wiki/Q7246855","display_name":"Probabilistic forecasting","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.02832","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02832","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.02832","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02832","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"forecasting":[1,91,115,223],"of":[2,63,112,132,216],"recovery":[3,200],"rates":[4],"(RR)":[5],"is":[6,23],"central":[7],"to":[8,40,196,220],"credit":[9,226],"risk":[10,233],"management":[11],"and":[12,61,66,72,103,135,156,182,228],"regulatory":[13],"capital":[14],"determination.":[15],"In":[16],"many":[17],"loan":[18,152],"portfolios,":[19],"however,":[20],"RR":[21,90,114,222],"modeling":[22],"constrained":[24],"by":[25,44],"data":[26,173,238],"scarcity":[27],"arising":[28],"from":[29,47],"infrequent":[30],"default":[31],"events.":[32],"Transfer":[33],"learning":[34],"(TL)":[35],"offers":[36],"a":[37,80,109,123,142,157],"promising":[38],"avenue":[39],"mitigate":[41],"this":[42],"challenge":[43],"exploiting":[45],"information":[46,204],"related":[48],"but":[49],"richer":[50,203],"source":[51,71,155],"domains,":[52],"yet":[53],"its":[54,193],"effectiveness":[55],"critically":[56],"depends":[57],"on":[58,67],"the":[59,119,147,211,214],"presence":[60],"strength":[62],"distributional":[64],"shifts,":[65,137,184],"potential":[68,215],"heterogeneity":[69],"between":[70],"target":[73],"feature":[74,94],"spaces.":[75],"This":[76],"paper":[77],"introduces":[78],"FT-MDN-Transformer,":[79],"mixture-density":[81],"tabular":[82],"Transformer":[83],"architecture":[84],"specifically":[85],"designed":[86],"for":[87,232],"TL":[88,218],"in":[89,122,141,224],"across":[92],"heterogeneous":[93,237],"sets.":[95],"The":[96],"model":[97],"produces":[98],"both":[99],"loan-level":[100],"point":[101],"estimates":[102],"portfolio-level":[104],"predictive":[105],"distributions,":[106,201],"thereby":[107],"supporting":[108],"wide":[110],"range":[111],"practical":[113,230],"applications.":[116],"We":[117,190],"evaluate":[118],"proposed":[120],"approach":[121],"controlled":[124],"Monte":[125],"Carlo":[126],"simulation":[127],"that":[128,166],"facilitates":[129],"systematic":[130],"variation":[131],"covariate,":[133],"conditional,":[134],"label":[136,186],"as":[138,140,154,161],"well":[139],"real-world":[143],"transfer":[144],"setting":[145],"using":[146],"Global":[148],"Credit":[149],"Data":[150],"(GCD)":[151],"dataset":[153,160],"novel":[158],"bonds":[159],"target.":[162],"Our":[163],"results":[164],"show":[165],"FT-MDN-Transformer":[167],"outperforms":[168],"baseline":[169],"models":[170],"when":[171],"target-domain":[172],"are":[174],"limited,":[175],"with":[176],"particularly":[177],"pronounced":[178],"gains":[179],"under":[180,236],"covariate":[181],"conditional":[183],"while":[185],"shift":[187],"remains":[188],"challenging.":[189],"also":[191],"observe":[192],"probabilistic":[194],"forecasts":[195],"closely":[197],"track":[198],"empirical":[199],"providing":[202],"than":[205],"conventional":[206],"point-prediction":[207],"metrics":[208],"alone.":[209],"Overall,":[210],"findings":[212],"highlight":[213],"distribution-aware":[217],"architectures":[219],"improve":[221],"data-scarce":[225],"portfolios":[227],"offer":[229],"insights":[231],"managers":[234],"operating":[235],"environments.":[239]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-07T00:00:00"}