{"id":"https://openalex.org/W655118345","doi":null,"title":"An efficient explanation of regression and classification models\u2019 predictions","display_name":"An efficient explanation of regression and classification models\u2019 predictions","alternate_titles":[],"publication_year":2011,"publication_date":"2011-10-14","ids":{"openalex":"https://openalex.org/W655118345","mag":"655118345"},"language":"en","primary_location":{"id":"mag:655118345","doi":null,"is_oa":false,"landing_page_url":"http://eprints.fri.uni-lj.si/1566/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W655118345"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077660248","display_name":"Erik \u0160trumbelj","orcid":"https://orcid.org/0000-0001-6071-0491","observed_orcids":["https://orcid.org/0000-0001-6071-0491"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Erik \u0160trumbelj","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6071-0491","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5077660248"],"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_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/explainable-machine-learning","display_name":"explainable machine learning","score":0.7590000033378601},{"id":"https://openalex.org/keywords/feature-contribution","display_name":"feature contribution","score":0.3440000116825104},{"id":"https://openalex.org/keywords/shapley-value","display_name":"Shapley value","score":0.7490000128746033},{"id":"https://openalex.org/keywords/interaction-effects","display_name":"interaction effects","score":0.5410000085830688},{"id":"https://openalex.org/keywords/approximation-algorithms","display_name":"approximation algorithms","score":0.5270000100135803},{"id":"https://openalex.org/keywords/selective-sampling","display_name":"selective sampling","score":0.9769999980926514},{"id":"https://openalex.org/keywords/quasi-random-sampling","display_name":"quasi-random sampling","score":0.9919999837875366},{"id":"https://openalex.org/keywords/model-agnostic-explanation","display_name":"model-agnostic explanation","score":0.6669999957084656},{"id":"https://openalex.org/keywords/regression-models","display_name":"regression models","score":0.621999979019165},{"id":"https://openalex.org/keywords/classification-models","display_name":"classification models","score":0.9990000128746033},{"id":"https://openalex.org/keywords/breast-cancer-recurrence","display_name":"breast cancer recurrence","score":0.9120000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936012506484985},{"id":"https://openalex.org/C199022921","wikidata":"https://www.wikidata.org/wiki/Q240046","display_name":"Shapley value","level":3,"score":0.5561545491218567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5256301760673523},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5015995502471924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4898318946361542},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4833964407444},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4407809376716614},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4130093455314636},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.311090350151062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20125997066497803},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13353541493415833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:655118345","doi":null,"is_oa":false,"landing_page_url":"http://eprints.fri.uni-lj.si/1566/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2097310377","https://openalex.org/W934500432","https://openalex.org/W2068840577","https://openalex.org/W2910882212","https://openalex.org/W3035738663","https://openalex.org/W2129888542","https://openalex.org/W2113211233","https://openalex.org/W3213492777","https://openalex.org/W7213597884","https://openalex.org/W2889295702"],"abstract_inverted_index":{"Providing":[0],"an":[1,7,152,250,266],"explanation":[2,281],"for":[3,61,271],"prediction":[4],"models":[5,203],"is":[6,129],"important":[8],"part":[9],"of":[10,21,29,64,74,77,91,120,166,212,243,284,292],"knowledge":[11],"discovery.":[12],"It":[13],"helps":[14],"with":[15,117,144,282],"a":[16,101,106,136,173,181,224],"quicker":[17],"and":[18,24,70,94,115,158,188,191,197,201,230,268,273,288],"better":[19],"understanding":[20],"the":[22,26,32,48,72,86,118,126,132,145,164,167,177,184,209,213,219,234,244,256,280,290,293],"model":[23],"increases":[25],"user's":[27,294],"level":[28],"trust":[30],"in":[31,95],"model's":[33,49],"predictions.":[34,295],"We":[35,104,123,142,154,170,216,237,247],"focus":[36],"on":[37],"methods,":[38],"which":[39,109,175,253],"assign":[40],"to":[41,47,99,131,161,179,206,223,259],"each":[42],"input":[43,92,285],"feature":[44],"its":[45],"contribution":[46],"prediction.":[50],"Most":[51],"such":[52],"methods":[53,80],"are":[54,195,204],"model-specific.":[55],"However,":[56],"some":[57],"can":[58],"be":[59],"used":[60,196],"any":[62],"type":[63],"model,":[65],"thus":[66],"simplifying":[67],"their":[68],"use":[69,155],"enabling":[71],"comparison":[73],"different":[75,199],"types":[76],"models.\r\n\r\nExisting":[78],"general":[79,107],"do":[81],"not":[82],"take":[83],"into":[84,113],"account":[85,114],"interactions":[87,112],"across":[88],"all":[89,111],"subsets":[90],"features":[93,286],"certain":[96],"cases":[97],"fail":[98],"provide":[100],"proper":[102],"explanation.":[103],"propose":[105,172],"method,":[108],"takes":[110],"deals":[116],"shortcomings":[119],"existing":[121],"methods.":[122],"prove":[124],"that":[125,279],"proposed":[127,214,245],"method":[128,220],"related":[130],"Shapley":[133],"value":[134],"-":[135],"well-known":[137],"concept":[138],"from":[139,261],"game":[140],"theory.":[141],"deal":[143],"resulting":[146],"exponential":[147],"time":[148,187],"complexity":[149],"by":[150],"using":[151],"approximation.":[153],"selective":[156],"sampling":[157,160],"quasi-random":[159],"further":[162],"improve":[163],"efficiency":[165],"approximation":[168],"algorithm.":[169],"also":[171,238,248],"mechanism,":[174],"allows":[176],"user":[178],"select":[180],"tradeoff":[182],"between":[183],"total":[185],"running":[186],"expected":[189],"error.\r\n\r\nSynthetic":[190],"real-world":[192,225],"data":[193],"sets":[194],"several":[198],"classification":[200],"regression":[202],"applied":[205,222],"empirically":[207],"show":[208],"practical":[210],"utility":[211],"method.":[215,246],"describe":[217],"how":[218,231],"was":[221],"breast":[226],"cancer":[227],"recurrence":[228],"problem":[229],"oncologists":[232],"confirmed":[233],"method's":[235],"usefulness.":[236],"list":[239],"other":[240],"successful":[241],"application":[242],"conducted":[249],"experiment,":[251],"during":[252],"we":[254],"tested":[255],"users'":[257],"ability":[258],"learn":[260],"examples":[262],"(with":[263],"or":[264],"without":[265],"explanation)":[267],"make":[269],"predictions":[270],"new":[272],"unknown":[274],"instances.":[275],"The":[276],"results":[277],"reveal":[278],"contributions":[283],"help":[287],"increase":[289],"accuracy":[291]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W655118345","counts_by_year":[],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2016-06-24T00:00:00"}
