{"id":"https://openalex.org/W7164027183","doi":"https://doi.org/10.48550/arxiv.2606.08896","title":"FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting","display_name":"FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164027183","doi":"https://doi.org/10.48550/arxiv.2606.08896"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08896","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.08896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138284882","display_name":"Qianyang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qianyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138244310","display_name":"Xingjun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xingjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077762154","display_name":"Shaoxun Wang","orcid":"https://orcid.org/0000-0002-1439-021X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shaoxun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138203859","display_name":"Tao Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138219055","display_name":"Jia Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Jia","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/T11918","display_name":"Forecasting Techniques and Applications","score":0.8395000100135803,"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"}},"topics":[{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.8395000100135803,"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"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.09030000120401382,"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"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.01510000042617321,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6845999956130981},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5569999814033508},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5242999792098999},{"id":"https://openalex.org/keywords/demand-forecasting","display_name":"Demand forecasting","score":0.5170999765396118},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.4846999943256378},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4830999970436096},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.4106999933719635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355999946594238},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6845999956130981},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5249000191688538},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C193809577","wikidata":"https://www.wikidata.org/wiki/Q3409300","display_name":"Demand forecasting","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5033000111579895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42089998722076416},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C133710760","wikidata":"https://www.wikidata.org/wiki/Q775837","display_name":"Exponential smoothing","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C120954023","wikidata":"https://www.wikidata.org/wiki/Q1127277","display_name":"Consensus forecast","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08896","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.08896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08896","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.48287296295166016}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"retail":[1,126],"and":[2,18,39,84,145,210],"industrial":[3,140],"forecasting":[4,25,60,114,199],"systems":[5],"contain":[6],"many":[7],"heterogeneous":[8,197],"time":[9],"series":[10,72,165],"whose":[11],"lifecycle,":[12],"sparsity,":[13],"volatility,":[14],"seasonality,":[15],"spectral":[16],"patterns,":[17],"contextual":[19],"sensitivity":[20],"differ":[21],"substantially.":[22],"A":[23],"single":[24,157],"model":[26,202],"rarely":[27],"performs":[28],"well":[29],"across":[30,135],"all":[31],"regimes,":[32],"while":[33,160,174],"dense":[34],"ensembles":[35],"increase":[36],"inference":[37],"cost":[38],"provide":[40],"limited":[41],"insight":[42],"into":[43,119,204],"expert":[44,50,131,211],"suitability.":[45],"This":[46],"paper":[47],"studies":[48],"forecastability-aware":[49],"routing:":[51],"learning":[52],"how":[53],"data":[54,136,205],"characteristics":[55],"determine":[56],"the":[57,113,120,139,155],"suitability":[58,132],"of":[59,96,207],"experts.":[61],"We":[62],"propose":[63],"\\method{},":[64],"a":[65,74,86,92,102,185],"sparse":[66,88],"mixture-of-experts":[67],"framework":[68,195],"that":[69,130],"represents":[70],"each":[71,99],"with":[73,124,142],"multidimensional":[75],"forecastability":[76,208],"fingerprint,":[77],"mines":[78],"expert-suitability":[79],"targets":[80],"from":[81,107,200],"validation":[82],"performance,":[83],"trains":[85],"cost-aware":[87],"router":[89],"to":[90],"activate":[91],"small":[93],"budgeted":[94],"set":[95],"experts":[97,163],"for":[98],"series.":[100],"Using":[101],"production-scale":[103],"vending-machine":[104],"sales":[105,198],"dataset":[106,141],"Shandong":[108],"New":[109],"Beiyang":[110],"(SNBC),":[111],"where":[112],"component":[115,170],"has":[116],"been":[117],"integrated":[118],"replenishment-planning":[121],"pipeline,":[122],"together":[123],"public":[125],"benchmarks,":[127],"we":[128],"show":[129],"varies":[133],"systematically":[134],"regimes.":[137],"On":[138],"5,000+":[143],"machines":[144],"60M+":[146],"transactions,":[147],"\\method{}":[148],"Top-2":[149],"reduces":[150],"MSE":[151],"by":[152,179,191],"12.4\\%":[153],"over":[154],"strongest":[156],"expert,":[158],"LightGBM,":[159],"executing":[161],"1.92":[162],"per":[164],"on":[166],"average.":[167],"The":[168,194],"deployed":[169],"produces":[171],"demand":[172],"forecasts,":[173],"inventory-oriented":[175],"gains":[176],"are":[177],"estimated":[178],"an":[180],"offline":[181],"replay":[182],"simulator":[183],"under":[184],"fixed":[186],"replenishment":[187],"policy":[188],"rather":[189],"than":[190],"online":[192],"intervention.":[193],"turns":[196],"heuristic":[201],"selection":[203],"mining":[206],"patterns":[209],"specialization.":[212],"Code":[213],"is":[214],"available":[215],"at":[216],"https://github.com/hit636/FAME":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}