{"id":"https://openalex.org/W4416017986","doi":"https://doi.org/10.1145/3746252.3761532","title":"Augmenting Limited and Biased RCTs through Pseudo-Sample Matching-Based Observational Data Fusion Method","display_name":"Augmenting Limited and Biased RCTs through Pseudo-Sample Matching-Based Observational Data Fusion Method","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017986","doi":"https://doi.org/10.1145/3746252.3761532"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761532","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5102542017","display_name":"Kairong Han","orcid":"https://orcid.org/0000-0003-0003-2312"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kairong Han","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0003-2312","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119962824","display_name":"Weidong Huang","orcid":"https://orcid.org/0009-0004-6704-5323"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Huang","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6704-5323","affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Taiyang Zhou","orcid":"https://orcid.org/0009-0005-1413-6771"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiyang Zhou","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-1413-6771","affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076780622","display_name":"\u5f6d\u771f PENG Zhen","orcid":"https://orcid.org/0009-0008-5062-3798"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhen","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5062-3798","affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041727387","display_name":"Kun Kuang","orcid":"https://orcid.org/0000-0001-7024-9790"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Kuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7024-9790","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102542017"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34489609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5715","last_page":"5722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.49410000443458557,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.49410000443458557,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.12409999966621399,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.040800001472234726,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/observational-study","display_name":"Observational study","score":0.7229999899864197},{"id":"https://openalex.org/keywords/randomized-controlled-trial","display_name":"Randomized controlled trial","score":0.52920001745224},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4986000061035156},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4366999864578247},{"id":"https://openalex.org/keywords/randomized-experiment","display_name":"Randomized experiment","score":0.40130001306533813},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.358599990606308},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.33640000224113464}],"concepts":[{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.7229999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133000254631042},{"id":"https://openalex.org/C168563851","wikidata":"https://www.wikidata.org/wiki/Q1436668","display_name":"Randomized controlled trial","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5006999969482422},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4366999864578247},{"id":"https://openalex.org/C155108698","wikidata":"https://www.wikidata.org/wiki/Q1231081","display_name":"Randomized experiment","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C176743888","wikidata":"https://www.wikidata.org/wiki/Q862797","display_name":"Observational methods in psychology","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2515000104904175},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761532","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3253937777","display_name":null,"funder_award_id":"62376243","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4842318824","display_name":null,"funder_award_id":"2024YFE0203700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1591419506","https://openalex.org/W1981886486","https://openalex.org/W2008733204","https://openalex.org/W2024668293","https://openalex.org/W2064903582","https://openalex.org/W2091873537","https://openalex.org/W2107602010","https://openalex.org/W2136132422","https://openalex.org/W2143474346","https://openalex.org/W2165558283","https://openalex.org/W2208550830","https://openalex.org/W2262207379","https://openalex.org/W2296609147","https://openalex.org/W2769861923","https://openalex.org/W2909452395","https://openalex.org/W3000364429","https://openalex.org/W3204398858","https://openalex.org/W4211219130","https://openalex.org/W4287597699","https://openalex.org/W4393156463","https://openalex.org/W4409150405","https://openalex.org/W4410088835"],"related_works":[],"abstract_inverted_index":{"In":[0,194,222],"the":[1,19,35,40,69,74,80,118,124,161,169,172,181,226,238,247,260,267],"online":[2,189,197,234],"ride-hailing":[3],"pricing":[4],"context,":[5,61],"companies":[6],"often":[7,87],"conduct":[8],"randomized":[9],"controlled":[10],"trials":[11],"(RCTs)":[12],"and":[13,94,123,157,188,233,245],"utilize":[14],"uplift":[15],"models":[16],"to":[17,34,46,68,89,100,109,117,130,213,228],"assess":[18],"effect":[20],"of":[21,38,42,56,76,82,121,218,249,259],"discounts":[22],"on":[23],"customer":[24],"orders,":[25],"which":[26,51,85,206],"substantially":[27],"influences":[28],"competitive":[29],"market":[30],"outcomes.":[31],"However,":[32],"due":[33,116],"high":[36,119],"cost":[37],"RCTs,":[39],"proportion":[41],"trial":[43],"data":[44,48,104,143,156,240,252],"relative":[45],"observational":[47,167],"is":[49,86,207,242],"small,":[50],"only":[52],"accounts":[53],"for":[54],"0.65%":[55],"total":[57],"traffic":[58],"in":[59,63,112,204,220,254,266],"our":[60],"resulting":[62],"significant":[64],"bias":[65],"when":[66,211,237],"generalizing":[67],"broader":[70],"user":[71],"base.":[72],"Additionally,":[73],"complexity":[75],"industrial":[77,114,214,255],"processes":[78],"reduces":[79],"quality":[81,241,253],"RCT":[83,155,173,239,251],"data,":[84,168],"subject":[88],"heterogeneity":[90],"from":[91,152,165],"potential":[92],"interference":[93],"selection":[95],"bias,":[96],"making":[97],"it":[98],"difficult":[99],"correct.":[101],"Moreover,":[102],"existing":[103],"fusion":[105,144],"methods":[106],"are":[107,128],"challenging":[108],"implement":[110],"effectively":[111],"complex":[113],"settings":[115],"dimensionality":[120],"features":[122],"strict":[125],"assumptions":[126],"that":[127],"hard":[129],"verify":[131],"with":[132,160,216],"real-world":[133,192],"data.":[134,193],"To":[135],"address":[136],"these":[137],"issues,":[138],"we":[139,199,224],"propose":[140],"an":[141],"empirical":[142],"method":[145,170,182],"called":[146],"pseudo-sample":[147],"matching.":[148],"By":[149],"generating":[150],"pseudo-samples":[151],"biased,":[153],"low-quality":[154],"matching":[158],"them":[159],"most":[162],"similar":[163],"samples":[164],"large-scale":[166],"expands":[171],"dataset":[174],"while":[175],"mitigating":[176],"its":[177],"heterogeneity.":[178],"We":[179],"validated":[180],"through":[183],"simulation":[184,261],"experiments,":[185],"conducted":[186],"offline":[187,231],"tests":[190],"using":[191],"a":[195,201,208],"week-long":[196],"experiment,":[198],"achieved":[200],"0.41%":[202],"improvement":[203],"profit,":[205],"considerable":[209],"gain":[210],"scaled":[212],"scenarios":[215],"hundreds":[217],"millions":[219],"revenue.":[221],"addition,":[223],"discuss":[225],"harm":[227],"model":[229],"training,":[230],"evaluation,":[232],"economic":[235],"benefits":[236],"not":[243],"high,":[244],"emphasize":[246],"importance":[248],"improving":[250],"scenarios.":[256],"Further":[257],"details":[258],"experiments":[262],"can":[263],"be":[264],"found":[265],"GitHub":[268],"repository":[269],"https://github.com/Kairong-Han/Pseudo-Matching.":[270]},"counts_by_year":[],"updated_date":"2025-11-08T23:25:12.792448","created_date":"2025-11-08T00:00:00"}