{"id":"https://openalex.org/W7134972536","doi":"https://doi.org/10.1109/icdmw69685.2025.00051","title":"Automated Indicator Mining and Forecast-Ready Feature Engineering via LLMs: Application in Colocation Data Center Supply Chains","display_name":"Automated Indicator Mining and Forecast-Ready Feature Engineering via LLMs: Application in Colocation Data Center Supply Chains","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134972536","doi":"https://doi.org/10.1109/icdmw69685.2025.00051"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","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/A5093764418","display_name":"Pegah Mavaie","orcid":null},"institutions":[{"id":"https://openalex.org/I86725329","display_name":"Hitachi Global Storage Technologies (United States)","ror":"https://ror.org/02q0s1x22","country_code":"US","type":"company","lineage":["https://openalex.org/I86725329"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pegah Mavaie","raw_affiliation_strings":["Hitachi R&D,SDSL Lab,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"Hitachi R&D,SDSL Lab,Santa Clara,USA","institution_ids":["https://openalex.org/I86725329"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072638150","display_name":"Neda Zarayeneh","orcid":null},"institutions":[{"id":"https://openalex.org/I86725329","display_name":"Hitachi Global Storage Technologies (United States)","ror":"https://ror.org/02q0s1x22","country_code":"US","type":"company","lineage":["https://openalex.org/I86725329"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neda Zarayeneh","raw_affiliation_strings":["Hitachi R&D,SDSL Lab,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"Hitachi R&D,SDSL Lab,Santa Clara,USA","institution_ids":["https://openalex.org/I86725329"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128789013","display_name":"Ravigopal Vennelakanti","orcid":null},"institutions":[{"id":"https://openalex.org/I86725329","display_name":"Hitachi Global Storage Technologies (United States)","ror":"https://ror.org/02q0s1x22","country_code":"US","type":"company","lineage":["https://openalex.org/I86725329"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravigopal Vennelakanti","raw_affiliation_strings":["Hitachi R&D,SDSL Lab,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"Hitachi R&D,SDSL Lab,Santa Clara,USA","institution_ids":["https://openalex.org/I86725329"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093764418"],"corresponding_institution_ids":["https://openalex.org/I86725329"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88611538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.32100000977516174,"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":0.32100000977516174,"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":0.08529999852180481,"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/T12127","display_name":"Software System Performance and Reliability","score":0.047600001096725464,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/feature","display_name":"Feature (linguistics)","score":0.5016999840736389},{"id":"https://openalex.org/keywords/supply-chain","display_name":"Supply chain","score":0.46059998869895935},{"id":"https://openalex.org/keywords/center","display_name":"Center (category theory)","score":0.3492000102996826},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.33250001072883606},{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.3215000033378601},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.29249998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57669997215271},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46959999203681946},{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C2779463800","wikidata":"https://www.wikidata.org/wiki/Q5062222","display_name":"Center (category theory)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2874000072479248},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27059999108314514}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4992752969264984,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2019459021","https://openalex.org/W2025610165","https://openalex.org/W2058715873","https://openalex.org/W2060422862","https://openalex.org/W2141975087","https://openalex.org/W2342249984","https://openalex.org/W2970641574","https://openalex.org/W3121403162","https://openalex.org/W3126081245","https://openalex.org/W4285392431","https://openalex.org/W4385245566","https://openalex.org/W4391781794","https://openalex.org/W4396865898","https://openalex.org/W4401780550","https://openalex.org/W4404489991","https://openalex.org/W4406072772","https://openalex.org/W4407506282"],"related_works":[],"abstract_inverted_index":{"The":[0,155],"strategic":[1],"planning":[2],"of":[3,12,36,49,66,88,94,130,143,162],"colocation":[4],"data":[5,125],"center":[6],"supply":[7],"chains":[8],"requires":[9],"the":[10,46,60,122,160,183,188],"synthesis":[11],"diverse":[13],"macroeconomic":[14],"and":[15,64,133,150,191,201],"industry-specific":[16],"signals,":[17],"a":[18,32,55,77,85,92,104,113,127,134,139,151,169,172,178,199],"task":[19],"that":[20,39],"is":[21,40],"critical":[22],"for":[23,59,204],"anticipating":[24],"market":[25],"dynamics.":[26],"Traditional":[27],"approaches,":[28],"however,":[29],"rely":[30],"on":[31,109],"manual,":[33],"artisanal":[34],"process":[35],"indicator":[37],"curation":[38],"neither":[41],"scalable":[42],"nor":[43],"adaptive":[44],"to":[45,82,120],"rapid":[47],"pace":[48],"technological":[50],"change.":[51],"This":[52,196],"paper":[53],"introduces":[54],"novel,":[56],"end-to-end":[57],"pipeline":[58,145],"automated":[61,205],"discovery,":[62],"validation,":[63],"retrieval":[65],"forecast-ready":[67],"economic":[68],"indicators":[69,90],"directly":[70],"from":[71,91,126],"unstructured":[72],"text.":[73],"Our":[74],"methodology":[75],"leverages":[76],"Large":[78],"Language":[79],"Model":[80],"(LLM)":[81],"first":[83],"identify":[84],"comprehensive":[86],"set":[87],"candidate":[89],"corpus":[93],"industry":[95],"reports.":[96],"These":[97],"candidates":[98],"are":[99],"then":[100],"quantitatively":[101],"validated":[102],"using":[103],"semantic":[105,164],"filtering":[106],"stage":[107],"based":[108],"embedding":[110],"similarity.":[111],"Finally,":[112],"second":[114],"LLM-based":[115],"module":[116],"generates":[117],"actionable":[118],"queries":[119],"retrieve":[121],"corresponding":[123],"time-series":[124],"multi-modal":[128],"system":[129],"high-authority":[131],"APIs":[132],"web-scraping":[135],"fallback.":[136],"We":[137],"conduct":[138],"rigorous":[140],"empirical":[141],"evaluation":[142],"our":[144,163],"against":[146],"an":[147],"expert-curated":[148],"benchmark":[149],"strong":[152],"keyword-based":[153],"baseline.":[154],"results":[156],"not":[157],"only":[158],"confirm":[159],"superiority":[161],"approach":[165],"but":[166],"also":[167],"reveal":[168],"key":[170],"insight:":[171],"direct,":[173],"zero-shot":[174],"prompting":[175],"strategy":[176],"with":[177],"smaller":[179],"model":[180],"(gpt-3.5-turbo)":[181],"achieves":[182],"highest":[184],"F1-Score,":[185],"outperforming":[186],"both":[187],"larger":[189],"GPT-4":[190],"more":[192],"complex":[193],"reasoning-based":[194],"prompts.":[195],"work":[197],"presents":[198],"new":[200],"generalizable":[202],"paradigm":[203],"feature":[206],"engineering":[207],"in":[208],"complex,":[209],"specialized":[210],"domains.":[211]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2026-03-12T00:00:00"}