{"id":"https://openalex.org/W2197738759","doi":"https://doi.org/10.1109/bigdata.2015.7364128","title":"Big data gathering and mining pipelines for CRM using open-source","display_name":"Big data gathering and mining pipelines for CRM using open-source","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2197738759","doi":"https://doi.org/10.1109/bigdata.2015.7364128","mag":"2197738759"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7364128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","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/A5100456986","display_name":"Kang Li","orcid":"https://orcid.org/0000-0002-8136-9816"},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kang Li","raw_affiliation_strings":["Search and Data Mining Groupon, Palo Alto, CA"],"affiliations":[{"raw_affiliation_string":"Search and Data Mining Groupon, Palo Alto, CA","institution_ids":["https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077747661","display_name":"Vinay Deolalikar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinay Deolalikar","raw_affiliation_strings":["Search and Data Mining Groupon, Palo Alto, CA"],"affiliations":[{"raw_affiliation_string":"Search and Data Mining Groupon, Palo Alto, CA","institution_ids":["https://openalex.org/I4210133358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059712957","display_name":"Neeraj Pradhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neeraj Pradhan","raw_affiliation_strings":["Search and Data Mining Groupon, Palo Alto, CA"],"affiliations":[{"raw_affiliation_string":"Search and Data Mining Groupon, Palo Alto, CA","institution_ids":["https://openalex.org/I4210133358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100456986"],"corresponding_institution_ids":["https://openalex.org/I4210133358"],"apc_list":null,"apc_paid":null,"fwci":3.1784,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92965219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"70","issue":null,"first_page":"2936","last_page":"2938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994000196456909,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994000196456909,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7979626655578613},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.77440345287323},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6239156126976013},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5395317673683167},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5190939903259277},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5142099857330322},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4839630424976349},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.46329817175865173},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4285367727279663},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36916714906692505},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3313502371311188},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1844644546508789},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10600611567497253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09509935975074768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979626655578613},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.77440345287323},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6239156126976013},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5395317673683167},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5190939903259277},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5142099857330322},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4839630424976349},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.46329817175865173},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4285367727279663},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36916714906692505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3313502371311188},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1844644546508789},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10600611567497253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09509935975074768},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7364128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1506285740","https://openalex.org/W1992889781","https://openalex.org/W2010279913","https://openalex.org/W2014756888","https://openalex.org/W2041325010","https://openalex.org/W2107117509","https://openalex.org/W2110086534","https://openalex.org/W2116762767","https://openalex.org/W2129714679","https://openalex.org/W2159094788","https://openalex.org/W2624304035","https://openalex.org/W6630198464"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"Customer":[0],"Relationship":[1],"Management":[2],"(CRM)":[3],"is":[4,135,196,209],"currently":[5],"the":[6,32,35,43,136,146,228],"fastest":[7],"growing":[8],"sector":[9],"of":[10,37,45,149,157],"enterprise":[11,61,117],"software,":[12],"estimated":[13],"to":[14,16,42,94,102],"increase":[15],"$36.5B":[17],"worldwide":[18],"by":[19,55],"2017.":[20],"CRM":[21,178],"technologies":[22,66,82],"increasingly":[23],"use":[24],"data":[25,39,50,106,119,137,182,198,211,233],"mining":[26,212],"primitives":[27],"across":[28],"multiple":[29],"applications.":[30,107,187],"At":[31],"same":[33],"time,":[34],"growth":[36],"big":[38,49,105,118],"has":[40],"led":[41],"evolution":[44],"an":[46],"open":[47,76,123],"source":[48,77,124],"software":[51],"stack":[52,98],"(primarily":[53],"powered":[54],"Apache":[56],"software)":[57],"that":[58,130,180,201,214],"rivals":[59],"traditional":[60],"database":[62],"(RDBMS)":[63],"stacks.":[64],"New":[65],"such":[67,83,142,150,231],"as":[68,84,232],"Kafka,":[69,203],"Storm,":[70,204],"HBase":[71],"have":[72,91,132],"significantly":[73],"enriched":[74],"this":[75,158,162],"stack,":[78],"alongside":[79],"more":[80],"established":[81],"Hadoop":[85,218],"MapReduce":[86],"and":[87,139,184,205,217,241],"Mahout.":[88],"Today,":[89],"enterprises":[90,131],"a":[92,169,174,197,210],"choice":[93],"make":[95],"regarding":[96],"which":[97],"they":[99],"will":[100],"choose":[101],"power":[103],"their":[104],"However,":[108],"there":[109],"are":[110,145],"no":[111],"published":[112],"studies":[113],"in":[114,141,227],"literature":[115],"on":[116],"pipelines":[120],"built":[121],"using":[122],"components":[125],"supporting":[126],"CRM.":[127],"Specific":[128],"questions":[129,167],"include:":[133],"how":[134],"processed":[138],"analyzed":[140],"pipelines?":[143,151],"What":[144],"building":[147],"blocks":[148],"How":[152],"long":[153],"does":[154],"each":[155],"step":[156],"processing":[159],"take?":[160],"In":[161],"work,":[163],"we":[164],"answer":[165],"these":[166],"for":[168,224,235],"large":[170],"scale":[171],"(serving":[172],"over":[173],"100M":[175],"customers)":[176],"industrial":[177],"pipeline":[179,189],"incorporates":[181],"mining,":[183],"serves":[185],"several":[186],"Our":[188],"has,":[190],"broadly,":[191],"two":[192],"parts.":[193],"The":[194,207],"first":[195],"gathering":[199],"part":[200,213,230],"uses":[202,215],"HBase.":[206],"second":[208,229],"Mahout":[216],"MapReduce.":[219],"We":[220],"also":[221],"provide":[222],"timings":[223],"common":[225],"tasks":[226],"preprocessing":[234],"machine":[236],"learning,":[237],"clustering,":[238],"reservoir":[239],"sampling,":[240],"frequent":[242],"itemset":[243],"extraction.":[244]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}