{"id":"https://openalex.org/W7225458685","doi":"https://doi.org/10.31235/osf.io/ym96w_v2","title":"Strategic Location and Survival Dynamics of Businesses in San Diego County: A Comparative Machine Learning and Geospatial Approach","display_name":"Strategic Location and Survival Dynamics of Businesses in San Diego County: A Comparative Machine Learning and Geospatial Approach","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225458685","doi":"https://doi.org/10.31235/osf.io/ym96w_v2"},"language":"en","primary_location":{"id":"doi:10.31235/osf.io/ym96w_v2","doi":"https://doi.org/10.31235/osf.io/ym96w_v2","is_oa":true,"landing_page_url":"https://doi.org/10.31235/osf.io/ym96w_v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401238","display_name":"SocArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"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/10.31235/osf.io/ym96w_v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121640574","display_name":"Kenier Ramirez","orcid":"https://orcid.org/0009-0001-9900-2473","observed_orcids":["https://orcid.org/0009-0001-9900-2473"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kenier Ramirez","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-9900-2473","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5121640574"],"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/T12851","display_name":"Firm Innovation and Growth","score":0.8032000064849854,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12851","display_name":"Firm Innovation and Growth","score":0.8032000064849854,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.050200000405311584,"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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.023499999195337296,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/business-survival","display_name":"business survival","score":0.9190000295639038},{"id":"https://openalex.org/keywords/business-closures","display_name":"business closures","score":0.609000027179718},{"id":"https://openalex.org/keywords/business-age","display_name":"business age","score":0.5289999842643738},{"id":"https://openalex.org/keywords/business-ownership-structure","display_name":"business ownership structure","score":0.8379999995231628},{"id":"https://openalex.org/keywords/business-density","display_name":"business density","score":0.6740000247955322},{"id":"https://openalex.org/keywords/lightgbm","display_name":"LightGBM","score":0.828000009059906},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.8270000219345093},{"id":"https://openalex.org/keywords/san-diego-county","display_name":"San Diego County","score":0.7120000123977661},{"id":"https://openalex.org/keywords/business-longevity","display_name":"business longevity","score":0.33899998664855957},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.652999997138977},{"id":"https://openalex.org/keywords/k-prototypes-clustering","display_name":"k-prototypes clustering","score":0.7480000257492065},{"id":"https://openalex.org/keywords/business-location-strategy","display_name":"business location strategy","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.7400000095367432},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6384000182151794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6201000213623047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.616599977016449},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5277000069618225},{"id":"https://openalex.org/C41856607","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"Geographic information system","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C2910321205","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geographically Weighted Regression","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31235/osf.io/ym96w_v2","doi":"https://doi.org/10.31235/osf.io/ym96w_v2","is_oa":true,"landing_page_url":"https://doi.org/10.31235/osf.io/ym96w_v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401238","display_name":"SocArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.31235/osf.io/ym96w_v2","doi":"https://doi.org/10.31235/osf.io/ym96w_v2","is_oa":true,"landing_page_url":"https://doi.org/10.31235/osf.io/ym96w_v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401238","display_name":"SocArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W3186333964","https://openalex.org/W4213279016","https://openalex.org/W7033399520","https://openalex.org/W7214810862","https://openalex.org/W2912411919","https://openalex.org/W4412170701","https://openalex.org/W6976662291","https://openalex.org/W7221130877","https://openalex.org/W4313315589","https://openalex.org/W3189985038"],"abstract_inverted_index":{"Background:":[0],"Municipal":[1],"business":[2,9,40,60,164,204,224,255],"registries":[3],"provide":[4],"valuable":[5],"information":[6],"for":[7,28],"examining":[8],"conditions":[10],"and":[11,38,69,78,88,115,157,166,179,193,218,226,241,272,275],"characteristics":[12],"associated":[13],"with":[14,52,253],"longevity.":[15],"However,":[16],"recorded":[17,36,59,254],"business-status":[18],"fields":[19],"do":[20],"not":[21,257],"necessarily":[22],"contain":[23],"complete":[24],"event":[25],"histories":[26],"required":[27],"formal":[29,283],"survival":[30,45,264,284],"analysis.":[31],"This":[32,47],"study":[33,48],"therefore":[34],"examines":[35],"active":[37],"closed/canceled":[39],"status":[41,61],"rather":[42],"than":[43],"time-to-event":[44],"probabilities.Purpose:":[46],"compares":[49],"logistic":[50],"regression":[51,170],"four":[53],"tree-based":[54],"ensemble":[55],"classifiers":[56,136,230],"to":[57,75,124,148,210,246,282],"distinguish":[58],"among":[62],"San":[63,299],"Diego":[64,300],"County":[65],"establishments.":[66],"SHAP":[67,145,202],"interpretation":[68],"unsupervised":[70],"clustering":[71],"are":[72],"also":[73],"used":[74,147],"examine":[76],"structural":[77],"geographic":[79,106,167],"patterns.Methods:":[80],"The":[81,93],"integrated":[82],"dataset":[83,96],"contained":[84],"158,330":[85],"initial":[86],"records":[87,103,271],"140,737":[89],"establishments":[90],"after":[91,100],"cleaning.":[92],"supervised":[94],"modeling":[95],"included":[97],"137,814":[98],"observations":[99,133],"excluding":[101],"2,923":[102],"without":[104],"valid":[105],"coordinates.":[107],"A":[108],"stratified":[109],"80/20":[110],"split":[111],"produced":[112],"110,251":[113],"training":[114,126],"27,563":[116],"holdout":[117,143,237],"test":[118],"observations.":[119],"SMOTE":[120],"was":[121,146],"applied":[122],"exclusively":[123],"the":[125,140,185,198,207,232,236],"data,":[127],"balancing":[128],"both":[129],"classes":[130],"at":[131],"69,998":[132],"each.":[134],"Five":[135],"were":[137],"evaluated":[138],"on":[139,235],"same":[141],"unaltered":[142],"set.":[144],"interpret":[149],"LightGBM":[150,183,211],"predictions,":[151,212],"while":[152],"K-Prototypes":[153],"(k":[154,160],"=":[155,161],"4)":[156],"spatial":[158,227],"K-Means":[159],"7)":[162],"characterized":[163],"profiles":[165,225],"patterns.Results:":[168],"Logistic":[169],"achieved":[171,184,197],"an":[172],"F1-score":[173,191],"of":[174,177,181,263],"0.587087,":[175],"accuracy":[176,187],"0.661834,":[178],"ROC-AUC":[180,194],"0.683970.":[182],"highest":[186,199],"(0.835679),":[188],"recall":[189],"(0.760220),":[190],"(0.792553),":[192],"(0.911295).":[195],"XGBoost":[196],"precision":[200],"(0.829190).":[201],"identified":[203,222],"age":[205,240],"as":[206],"strongest":[208],"contributor":[209],"followed":[213],"by":[214],"ownership,":[215],"density,":[216],"geographic,":[217],"industry":[219],"features.":[220],"Clustering":[221],"distinct":[223],"concentrations.Conclusions:":[228],"Ensemble":[229],"outperformed":[231],"logistic-regression":[233],"baseline":[234],"dataset.":[238],"Business":[239,286,289,297],"ownership":[242],"structure":[243],"contributed":[244],"substantially":[245],"model":[247],"predictions.":[248],"These":[249],"findings":[250],"represent":[251],"associations":[252],"status,":[256],"causal":[258],"effects":[259],"or":[260],"direct":[261],"estimates":[262],"over":[265],"time.":[266],"Future":[267],"research":[268],"using":[269],"longitudinal":[270],"verified":[273],"opening":[274],"closure":[276],"dates":[277],"could":[278],"extend":[279],"this":[280],"framework":[281],"analysis.Keywords:":[285],"Status":[287],"Classification;":[288],"Survival;":[290],"Machine":[291],"Learning;":[292],"LightGBM;":[293],"SHAP;":[294],"Spatial":[295],"Analysis;":[296],"Clustering;":[298],"County.":[301]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}