{"id":"https://openalex.org/W6982576477","doi":null,"title":"Interpretable Machine Learning for Insurance Risk Pricing","display_name":"Interpretable Machine Learning for Insurance Risk Pricing","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6982576477"},"language":"en","primary_location":{"id":"pmh:oai:DiVA.org:kth-345035","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-345035","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1849167/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kth.diva-portal.org/smash/get/diva2:1849167/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Darke, Felix","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Darke, Felix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":true,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12394","display_name":"Insurance and Financial Risk Management","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"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":0.0,"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/model-interpretability","display_name":"model interpretability","score":0.8360000252723694},{"id":"https://openalex.org/keywords/tabular-regression","display_name":"tabular regression","score":0.7310000061988831},{"id":"https://openalex.org/keywords/explainable-boosting-machine","display_name":"explainable boosting machine","score":0.8539999723434448},{"id":"https://openalex.org/keywords/generalized-additive-models","display_name":"generalized additive models","score":0.8500000238418579},{"id":"https://openalex.org/keywords/gradient-boosted-regression-trees","display_name":"gradient boosting regression tree","score":0.902999997138977},{"id":"https://openalex.org/keywords/basis-expansion","display_name":"basis function expansion","score":0.8799999952316284},{"id":"https://openalex.org/keywords/black-box-modeling","display_name":"black-box models","score":0.5619999766349792},{"id":"https://openalex.org/keywords/model-comparison","display_name":"model comparison","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9254000186920166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7511000037193298},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.7436000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.676800012588501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5629000067710876},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C203223496","wikidata":"https://www.wikidata.org/wiki/Q4681344","display_name":"Additive model","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2596000134944916},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:DiVA.org:kth-345035","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-345035","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1849167/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-345035","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-345035","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1849167/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6982576477.pdf","grobid_xml":"https://content.openalex.org/works/W6982576477.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W2149033360","https://openalex.org/W2973631113"],"related_works":["https://openalex.org/W3025517486","https://openalex.org/W3122287204","https://openalex.org/W4411309614","https://openalex.org/W4414903687","https://openalex.org/W4417504595","https://openalex.org/W7170085074","https://openalex.org/W7164031421","https://openalex.org/W7202248890","https://openalex.org/W7211883491","https://openalex.org/W7125505451"],"abstract_inverted_index":{"This":[0],"Master's":[1],"Thesis":[2],"project":[3,36,200],"set":[4,71],"out":[5],"with":[6,59],"the":[7,20,30,35,70,97,102,123,132,165,180,190,199,204,207,215,240,255,262,269,275,291,297,301,308,321,332],"objective":[8],"to":[9,41,235,287,314,331],"propose":[10],"a":[11,54,119,172,220,317],"machine":[12],"learning":[13],"model":[14,174,223,303],"for":[15,92,131,142,225],"predicting":[16],"insurance":[17],"risk":[18],"at":[19,198],"level":[21],"of":[22,72,177,183,239,320],"an":[23,226,246],"individual":[24],"coverage,":[25],"and":[26,86,164],"compare":[27],"it":[28,44,65],"towards":[29,261],"existing":[31],"models":[32,74,81,146,277,328],"used":[33,197,213],"by":[34,117,214,307],"provider":[37],"Gjensidige":[38],"F\u00f6rs\u00e4kring.":[39],"Due":[40],"interpretability":[42,103,113],"constraints,":[43],"was":[45,66],"found":[46],"that":[47,69,112,147,153,206,268,300],"this":[48,135],"problem":[49],"can":[50,114],"be":[51,115],"translated":[52],"into":[53],"standard":[55],"tabular":[56,93],"regression":[57,156,210,309],"task,":[58],"well":[60,237],"defined":[61],"target":[62],"distributions.":[63],"However,":[64],"early":[67],"identified":[68],"feasible":[73],"do":[75],"not":[76],"contain":[77],"pure":[78],"black":[79],"box":[80],"such":[82],"as":[83],"XGBoost,":[84],"LightGBM":[85],"CatBoost":[87],"which":[88,127,194,232,324],"are":[89,129,283],"typical":[90],"choices":[91],"data":[94,228],"regression.":[95],"In":[96],"report,":[98],"we":[99,128,137,151,244],"explicitly":[100],"formulate":[101],"constraints":[104],"in":[105,162,169,296,329],"sharp":[106],"mathematical":[107],"language.":[108],"It":[109],"is":[110,171,189,195,219,233,259,299],"concluded":[111],"ensured":[116],"enforcing":[118],"particular":[120],"structure":[121],"on":[122,249,278],"Hilbert":[124,181,322],"space":[125,182,323],"across":[126],"looking":[130],"model.":[133],"Using":[134],"formalism,":[136],"consider":[138],"two":[139],"different":[140,251],"approaches":[141],"fitting":[143,304],"high":[144],"performing":[145],"maintain":[148],"interpretability,":[149],"where":[150,254],"conclude":[152],"gradient":[154,208],"boosted":[155,209],"tree":[157,211,310],"based":[158],"Generalized":[159],"Additive":[160],"Models":[161],"general,":[163],"Explainable":[166,216,256,270],"Boosting":[167,217,257,271],"Machine":[168,218,258,272],"particular,":[170],"promising":[173],"candidate":[175],"consisting":[176],"functions":[178],"within":[179],"interest.":[184],"The":[185],"other":[186],"approach":[187,212,231,311],"considered":[188],"basis":[191,333],"expansion":[192,334],"approach,":[193],"currently":[196],"provider.":[201],"We":[202,266],"make":[203],"argument":[205],"more":[221],"suitable":[222],"type":[224],"automated,":[227],"driven":[229],"modelling":[230],"likely":[234],"generalize":[236],"outside":[238],"training":[241],"set.":[242],"Finally,":[243],"perform":[245],"empirical":[247],"study":[248],"three":[250],"internal":[252],"datasets,":[253],"compared":[260],"current":[263,276],"production":[264],"models.":[265],"find":[267],"systematically":[273],"outperforms":[274],"unseen":[279],"test":[280],"data.":[281],"There":[282],"many":[284],"potential":[285],"ways":[286],"explain":[288],"this,":[289],"but":[290],"main":[292],"hypothesis":[293],"brought":[294],"forward":[295],"report":[298],"sequential":[302],"procedure":[305],"allowed":[306],"allows":[312],"us":[313],"effectively":[315],"explore":[316],"larger":[318],"portion":[319],"contains":[325],"all":[326],"permitted":[327],"comparison":[330],"approach.":[335]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}