{"id":"https://openalex.org/W7163517377","doi":"https://doi.org/10.48550/arxiv.2606.04387","title":"Rethinking Sales Lead Scoring with LLM-based Hierarchical Preference Ranking","display_name":"Rethinking Sales Lead Scoring with LLM-based Hierarchical Preference Ranking","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163517377","doi":"https://doi.org/10.48550/arxiv.2606.04387"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.04387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100377496","display_name":"Chenyu Zhang","orcid":"https://orcid.org/0009-0000-3604-0643"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137896893","display_name":"Yiwen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137847904","display_name":"Yin Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137900286","display_name":"Xinyuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137814193","display_name":"Yuji Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yuji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137850042","display_name":"Junming Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Junming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137810608","display_name":"Juyi Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Juyi","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":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/T10203","display_name":"Recommender Systems and Techniques","score":0.4611999988555908,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.4611999988555908,"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"}},{"id":"https://openalex.org/T12384","display_name":"Customer churn and segmentation","score":0.10260000079870224,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.052799999713897705,"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/pointwise","display_name":"Pointwise","score":0.7258999943733215},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7074000239372253},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6793000102043152},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5444999933242798},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5288000106811523},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5127000212669373},{"id":"https://openalex.org/keywords/lead","display_name":"Lead (geology)","score":0.42800000309944153}],"concepts":[{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.7258999943733215},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5885000228881836},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.4242999851703644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35839998722076416},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C86532276","wikidata":"https://www.wikidata.org/wiki/Q1184065","display_name":"Delegation","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C85461838","wikidata":"https://www.wikidata.org/wiki/Q7100785","display_name":"Ordinal data","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.04387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"sustainable_development_goals":[{"score":0.6338748335838318,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sales":[0],"lead":[1,24,52,70,97,126,151],"conversion":[2],"in":[3,43],"high-stakes":[4],"domains":[5],"(e.g.,":[6],"automotive,":[7],"real":[8],"estate)":[9],"differs":[10],"fundamentally":[11],"from":[12,164],"e-commerce":[13],"recommendation":[14],"due":[15],"to":[16,49,140,153],"prolonged":[17],"decision":[18],"cycles":[19],"and":[20,47,79,107,157,174],"multi-stage":[21],"funnels.":[22,88],"Traditional":[23],"scoring":[25,127,152],"methods":[26],"rule-based":[27],"scorecards,":[28],"machine":[29],"learning,":[30],"or":[31],"pointwise":[32,156],"CTR":[33],"models":[34],"face":[35],"severe":[36],"challenges:":[37],"sparse":[38,142],"supervision,":[39],"a":[40,129,136,165],"semantic":[41,60],"gap":[42],"unstructured":[44,108],"CRM":[45,105],"logs,":[46],"inability":[48],"capture":[50],"relative":[51],"priority.":[53],"While":[54],"Large":[55],"Language":[56],"Models(LLMs)":[57],"offer":[58],"superior":[59],"understanding":[61],"of":[62,86,103,113],"customer":[63,109],"interactions,":[64],"general-purpose":[65],"LLMs":[66],"are":[67],"ill-suited":[68],"for":[69,95],"ranking:":[71],"they":[72],"generate":[73],"text":[74],"rather":[75],"than":[76],"comparable":[77],"scores,":[78],"lack":[80],"alignment":[81],"with":[82,128],"the":[83],"hierarchical":[84,130],"priorities":[85],"sales":[87,96,125,189],"We":[89],"introduce":[90],"an":[91],"LLM-based":[92],"discriminative":[93],"framework":[94],"scoring,":[98],"which":[99,123],"supports":[100],"joint":[101],"modeling":[102],"structured":[104],"features":[106],"interactions.":[110],"On":[111],"top":[112],"this":[114],"framework,":[115],"we":[116],"propose":[117],"HPRO":[118,134],"(Hierarchical":[119],"Preference":[120],"Ranking":[121],"Optimization),":[122],"augments":[124],"preference":[131,148],"ranking":[132,175],"objective.":[133],"employs":[135],"margin-aware":[137],"Bradley-Terry":[138],"formulation":[139],"transform":[141],"binary":[143],"labels":[144],"into":[145],"dense,":[146],"funnel-aware":[147],"pairs,":[149],"enabling":[150],"leverage":[154],"both":[155],"pairwise":[158],"supervision.":[159],"Experiments":[160],"on":[161],"large-scale":[162],"data":[163],"leading":[166],"NEV":[167],"brand":[168],"demonstrate":[169],"state-of-the-art":[170],"classification":[171],"(AUC":[172],"0.8161)":[173],"performance":[176],"(+39.7%":[177],"precision":[178],"among":[179],"top-ranked":[180],"leads).":[181],"A":[182],"132-day":[183],"online":[184],"A/B":[185],"test":[186],"validates":[187],"9.5%":[188],"volume":[190],"uplift,":[191],"confirming":[192],"real-world":[193],"commercial":[194],"impact.":[195]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-05T00:00:00"}