{"id":"https://openalex.org/W2955914872","doi":"https://doi.org/10.7287/peerj.preprints.27712v1","title":"Sales forecasting using multivariate long short term memory network models","display_name":"Sales forecasting using multivariate long short term memory network models","publication_year":2019,"publication_date":"2019-05-08","ids":{"openalex":"https://openalex.org/W2955914872","doi":"https://doi.org/10.7287/peerj.preprints.27712v1","mag":"2955914872"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.27712v1","doi":"https://doi.org/10.7287/peerj.preprints.27712v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27712v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7287/peerj.preprints.27712v1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082949817","display_name":"Suleka Helmini","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210141744","display_name":"WSO2 (Sri Lanka)","ror":"https://ror.org/037w3ea30","country_code":"LK","type":"company","lineage":["https://openalex.org/I4210141744"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Suleka Helmini","raw_affiliation_strings":["WSO2 Research, WSO2, Colombo, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WSO2 Research, WSO2, Colombo, Sri Lanka","institution_ids":["https://openalex.org/I4210141744"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045829972","display_name":"Nadheesh Jihan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210141744","display_name":"WSO2 (Sri Lanka)","ror":"https://ror.org/037w3ea30","country_code":"LK","type":"company","lineage":["https://openalex.org/I4210141744"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Nadheesh Jihan","raw_affiliation_strings":["WSO2 Research, WSO2, Colombo, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WSO2 Research, WSO2, Colombo, Sri Lanka","institution_ids":["https://openalex.org/I4210141744"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066398360","display_name":"Malith Jayasinghe","orcid":"https://orcid.org/0009-0000-9252-1943","observed_orcids":["https://orcid.org/0009-0000-9252-1943"]},"institutions":[{"id":"https://openalex.org/I4210141744","display_name":"WSO2 (Sri Lanka)","ror":"https://ror.org/037w3ea30","country_code":"LK","type":"company","lineage":["https://openalex.org/I4210141744"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Malith Jayasinghe","raw_affiliation_strings":["WSO2 Research, WSO2, Colombo, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WSO2 Research, WSO2, Colombo, Sri Lanka","institution_ids":["https://openalex.org/I4210141744"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5141206953","display_name":"Srinath Perera","orcid":"https://orcid.org/0000-0002-4457-903X","observed_orcids":["https://orcid.org/0000-0002-4457-903X","https://orcid.org/0000-0001-9218-9282"]},"institutions":[{"id":"https://openalex.org/I4210141744","display_name":"WSO2 (Sri Lanka)","ror":"https://ror.org/037w3ea30","country_code":"LK","type":"company","lineage":["https://openalex.org/I4210141744"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Srinath Perera","raw_affiliation_strings":["CTO Office, WSO2, Colombo 03, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CTO Office, WSO2, Colombo 03, Sri Lanka","institution_ids":["https://openalex.org/I4210141744"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210141744"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"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":0.9932000041007996,"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":0.9932000041007996,"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":0.00430000014603138,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/sales-forecasting","display_name":"sales forecasting","score":0.9980000257492065},{"id":"https://openalex.org/keywords/retail-demand-forecasting","display_name":"retail demand forecasting","score":0.7889999747276306},{"id":"https://openalex.org/keywords/long-short-term-memory-networks","display_name":"long short-term memory networks","score":0.8870000243186951},{"id":"https://openalex.org/keywords/deep-learning-time-series-forecasting","display_name":"deep learning time series forecasting","score":0.7400000095367432},{"id":"https://openalex.org/keywords/nonlinear-time-series","display_name":"nonlinear time series","score":0.6449999809265137},{"id":"https://openalex.org/keywords/xgboost-comparison","display_name":"XGBoost comparison","score":0.7960000038146973},{"id":"https://openalex.org/keywords/arima-model-comparison","display_name":"ARIMA comparison","score":0.7089999914169312}],"concepts":[{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.8118964433670044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505263090133667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6267619729042053},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6235107779502869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.610220730304718},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5822964310646057},{"id":"https://openalex.org/C2984642479","wikidata":"https://www.wikidata.org/wiki/Q7404320","display_name":"Sales forecasting","level":2,"score":0.5619330406188965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5425477623939514},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.5288389921188354},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.4820764660835266},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4647046625614166},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4427056908607483},{"id":"https://openalex.org/C2780150128","wikidata":"https://www.wikidata.org/wiki/Q21948731","display_name":"Extreme learning machine","level":3,"score":0.43503338098526},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43125060200691223},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.4299495816230774},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.4081210494041443},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.39132601022720337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09980511665344238}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.27712v1","doi":"https://doi.org/10.7287/peerj.preprints.27712v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27712v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.27712v1","doi":"https://doi.org/10.7287/peerj.preprints.27712v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27712v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1598796236","https://openalex.org/W1972221278","https://openalex.org/W2000765441","https://openalex.org/W2008056655","https://openalex.org/W2032582015","https://openalex.org/W2032990778","https://openalex.org/W2064675550","https://openalex.org/W2117014758","https://openalex.org/W2136848157","https://openalex.org/W2147939709","https://openalex.org/W2585503147","https://openalex.org/W2766441215","https://openalex.org/W2900296094","https://openalex.org/W2911964244","https://openalex.org/W2964170972","https://openalex.org/W3102476541"],"related_works":["https://openalex.org/W3170395704","https://openalex.org/W7079438340","https://openalex.org/W7210453639","https://openalex.org/W2785859583","https://openalex.org/W3004524957","https://openalex.org/W4406372161","https://openalex.org/W3128503814","https://openalex.org/W7202257442","https://openalex.org/W4390639768","https://openalex.org/W2979515705"],"abstract_inverted_index":{"In":[0,145],"the":[1,5,25,55,182,195,209,213,221,229,253,263,274,297],"retail":[2],"domain,":[3],"estimating":[4],"sales":[6,9,40,167,178],"before":[7],"actual":[8],"become":[10],"known":[11,225],"plays":[12],"a":[13,18,150,290],"key":[14],"role":[15],"in":[16,127,228,239],"maintaining":[17],"successful":[19],"business.":[20],"This":[21],"is":[22,224],"due":[23,134],"to":[24,33,104,130,135,138,226,273,296],"fact":[26],"that":[27,115,219,223,234,283],"most":[28,56],"crucial":[29],"decisions":[30],"are":[31,67,79],"bound":[32],"be":[34,50],"based":[35,243],"on":[36],"these":[37,65],"forecasts.":[38],"Statistical":[39],"forecasting":[41,61,244],"models":[42,66,89,118,133,256],"like":[43],"ARIMA":[44],"(Auto-Regressive":[45],"Integrated":[46],"Moving":[47],"Average),":[48],"can":[49,123,288],"identified":[51],"as":[52,91,100],"one":[53],"of":[54,69,153,184,212],"traditional":[57],"and":[58,141,201],"commonly":[59],"used":[60],"methodologies.":[62],"Even":[63],"though":[64],"capable":[68],"producing":[70],"satisfactory":[71],"forecasts":[72],"for":[73,82,166,177],"linear":[74],"time":[75],"series":[76],"data":[77],"they":[78,101],"not":[80,236],"suitable":[81],"analyzing":[83],"non-linear":[84,109],"data.":[85,110],"Therefore,":[86],"machine":[87,131,191,254,276],"learning":[88,117,132,192,255,277],"(such":[90],"Random":[92,202],"Forest":[93,203],"Regression,":[94],"XGBoost)":[95],"have":[96],"been":[97,237],"employed":[98],"frequently":[99],"were":[102],"able":[103],"achieve":[105],"better":[106],"results":[107,183],"using":[108,174],"The":[111,246],"recent":[112],"research":[113],"shows":[114],"deep":[116],"(e.g.":[119],"recurrent":[120],"neural":[121],"networks)":[122],"provide":[124],"higher":[125],"accuracy":[126,211],"predictions":[128],"compared":[129,272,295],"their":[136],"ability":[137],"persist":[139],"information":[140],"identify":[142],"temporal":[143],"relationships.":[144],"this":[146,185],"paper,":[147],"we":[148,250,280],"adopt":[149],"special":[151],"variant":[152],"Long":[154],"Short":[155],"Term":[156],"Memory":[157],"(LSTM)":[158],"network":[159],"called":[160],"LSTM":[161,187,242,248,265,286,299],"model":[162,173,188,199,215,249,266,287],"with":[163,189],"peephole":[164],"connections":[165],"prediction.":[168],"We":[169,180,206],"first":[170],"build":[171],"our":[172,284],"historical":[175],"features":[176,218],"forecasting.":[179],"compare":[181],"initial":[186,214,247,298],"multiple":[190],"models,":[193],"namely,":[194],"Extreme":[196],"Gradient":[197],"Boosting":[198],"(XGB)":[200],"Regressor":[204],"model(RFR).":[205],"further":[207],"improve":[208],"prediction":[210],"by":[216],"incorporating":[217],"describe":[220],"future":[222],"us":[227],"current":[230],"moment,":[231],"an":[232],"approach":[233],"has":[235],"explored":[238],"previous":[240],"state-of-the-art":[241],"models.":[245,278],"develop":[251],"outperforms":[252],"achieving":[257,301],"12%":[258],"-":[259,269,292],"14%":[260],"improvement":[261,271,294],"whereas":[262],"improved":[264,275,285],"achieves":[267],"11\\%":[268],"13\\%":[270],"Furthermore,":[279],"also":[281],"show":[282],"obtain":[289],"20%":[291],"21%":[293],"model,":[300],"significant":[302],"improvement.":[303]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-12T00:00:00"}