{"id":"https://openalex.org/W1969675113","doi":"https://doi.org/10.1145/1835804.1835834","title":"Estimating rates of rare events with multiple hierarchies through scalable log-linear models","display_name":"Estimating rates of rare events with multiple hierarchies through scalable log-linear models","publication_year":2010,"publication_date":"2010-07-25","ids":{"openalex":"https://openalex.org/W1969675113","doi":"https://doi.org/10.1145/1835804.1835834","mag":"1969675113"},"language":"en","primary_location":{"id":"doi:10.1145/1835804.1835834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049420901","display_name":"Deepak Agarwal","orcid":"https://orcid.org/0000-0003-2881-1254"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Deepak Agarwal","raw_affiliation_strings":["Yahoo!, Sunnyvale, CA, USA","Yahoo!, Sunnyvale, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039560708","display_name":"Rahul Agrawal","orcid":"https://orcid.org/0000-0002-3129-6698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahul Agrawal","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045284674","display_name":"Rajiv Khanna","orcid":"https://orcid.org/0000-0003-1314-3126"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajiv Khanna","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022658391","display_name":"Nagaraj Kota","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nagaraj Kota","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9994000196456909,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9994000196456909,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7733581066131592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695490121841431},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7138776779174805},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6843634843826294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6687636375427246},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.5276340842247009},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5070450305938721},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48988765478134155},{"id":"https://openalex.org/keywords/univariate","display_name":"Univariate","score":0.45873701572418213},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43423986434936523},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.4238257110118866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4194663465023041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3310369551181793},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08355924487113953}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7733581066131592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695490121841431},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7138776779174805},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6843634843826294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6687636375427246},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.5276340842247009},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5070450305938721},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48988765478134155},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.45873701572418213},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43423986434936523},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4238257110118866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4194663465023041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3310369551181793},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08355924487113953},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1835804.1835834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1554544485","https://openalex.org/W1969415786","https://openalex.org/W1973628995","https://openalex.org/W1974778955","https://openalex.org/W1997628954","https://openalex.org/W2054553473","https://openalex.org/W2070996757","https://openalex.org/W2071488943","https://openalex.org/W2083991698","https://openalex.org/W2090883204","https://openalex.org/W2132708887","https://openalex.org/W2140160814","https://openalex.org/W2157355837","https://openalex.org/W2170712385","https://openalex.org/W2294062369","https://openalex.org/W2338406834","https://openalex.org/W4302853952"],"related_works":["https://openalex.org/W2049578243","https://openalex.org/W1828158523","https://openalex.org/W2122079181","https://openalex.org/W2000145235","https://openalex.org/W1985848810","https://openalex.org/W2889939530","https://openalex.org/W2399195672","https://openalex.org/W3121881699","https://openalex.org/W2748838164","https://openalex.org/W2066015000"],"abstract_inverted_index":{"We":[0,39,129],"consider":[1],"the":[2],"problem":[3],"of":[4,7,55,153,155],"estimating":[5],"rates":[6],"rare":[8],"events":[9],"for":[10],"high":[11],"dimensional,":[12],"multivariate":[13],"categorical":[14],"data":[15,27,51,135],"where":[16],"several":[17,26,59,148],"dimensions":[18],"are":[19,23],"hierarchical.":[20],"Such":[21],"problems":[22],"routine":[24],"in":[25,36,63,71,166],"mining":[28],"applications":[29,52,140],"including":[30],"computational":[31,138],"advertising,":[32],"our":[33,103,143],"main":[34],"focus":[35],"this":[37],"paper.":[38],"propose":[40],"LMMH,":[41],"a":[42,64,113],"novel":[43],"log-linear":[44],"modeling":[45],"method":[46,68,104],"that":[47,118],"scales":[48],"to":[49,91],"massive":[50],"with":[53,79,147,159],"billions":[54],"training":[56],"records":[57,150],"and":[58,101,115,141,151],"million":[60],"potential":[61],"predictors":[62,124],"map-reduce":[65],"framework.":[66],"Our":[67],"exploits":[69],"correlations":[70],"aggregates":[72],"observed":[73],"at":[74,84,94],"multiple":[75,80],"resolutions":[76],"when":[77],"working":[78],"hierarchies;":[81],"stable":[82],"estimates":[83,93],"coarser":[85],"resolution":[86],"provide":[87],"informative":[88],"prior":[89],"information":[90],"improve":[92],"finer":[95],"resolutions.":[96],"Other":[97],"than":[98],"prediction":[99,167],"accuracy":[100],"scalability,":[102],"has":[105],"an":[106],"inbuilt":[107],"variable":[108],"screening":[109],"procedure":[110],"based":[111],"on":[112,134,145],"\"spike":[114],"slab":[116],"prior\"":[117],"provides":[119],"parsimony":[120],"by":[121],"removing":[122],"non-informative":[123],"without":[125],"hurting":[126],"predictive":[127],"accuracy.":[128,168],"perform":[130],"large":[131],"scale":[132],"experiments":[133],"from":[136],"real":[137],"advertising":[139],"illustrate":[142],"approach":[144],"datasets":[146],"billion":[149],"hundreds":[152],"millions":[154],"predictors.":[156],"Extensive":[157],"comparisons":[158],"other":[160],"benchmark":[161],"methods":[162],"show":[163],"significant":[164],"improvements":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}