{"id":"https://openalex.org/W4415564779","doi":"https://doi.org/10.56347/jics.v4i2.303","title":"Clustering and Classification of Retail Sales Data: A Big Data and Data Mining Analysis","display_name":"Clustering and Classification of Retail Sales Data: A Big Data and Data Mining Analysis","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415564779","doi":"https://doi.org/10.56347/jics.v4i2.303"},"language":"en","primary_location":{"id":"doi:10.56347/jics.v4i2.303","doi":"https://doi.org/10.56347/jics.v4i2.303","is_oa":true,"landing_page_url":"https://doi.org/10.56347/jics.v4i2.303","pdf_url":"https://journal.kawanad.com/index.php/jics/article/download/303/257","source":{"id":"https://openalex.org/S4387283372","display_name":"Journal Innovations Computer Science","issn_l":"2961-970X","issn":["2961-970X","2961-9718"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal Innovations Computer Science","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journal.kawanad.com/index.php/jics/article/download/303/257","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076788401","display_name":"Ahmad Bilal Almagribi","orcid":"https://orcid.org/0000-0001-6004-3422","observed_orcids":["https://orcid.org/0000-0001-6004-3422"]},"institutions":[{"id":"https://openalex.org/I4405258774","display_name":"Universitas Teknologi Digital Indonesia","ror":"https://ror.org/0169jeb69","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405258774"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ahmad Bilal Almagribi","raw_affiliation_strings":["Universitas Teknologi Digital Indonesia"],"raw_orcid":"https://orcid.org/0000-0001-6004-3422","affiliations":[{"raw_affiliation_string":"Universitas Teknologi Digital Indonesia","institution_ids":["https://openalex.org/I4405258774"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101745593","display_name":"Sri Redjeki","orcid":"https://orcid.org/0000-0002-2312-2743","observed_orcids":["https://orcid.org/0000-0002-2312-2743"]},"institutions":[{"id":"https://openalex.org/I4405258774","display_name":"Universitas Teknologi Digital Indonesia","ror":"https://ror.org/0169jeb69","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405258774"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Sri Redjeki","raw_affiliation_strings":["Universitas Teknologi Digital Indonesia"],"raw_orcid":"https://orcid.org/0000-0002-2312-2743","affiliations":[{"raw_affiliation_string":"Universitas Teknologi Digital Indonesia","institution_ids":["https://openalex.org/I4405258774"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405258774"],"apc_list":null,"apc_paid":null,"fwci":0.5862,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67210021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"4","issue":"2","first_page":"242","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.9380000233650208,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.9380000233650208,"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/T12384","display_name":"Customer churn and segmentation","score":0.05719999969005585,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/retail-sales-data","display_name":"retail sales data","score":0.9879999756813049},{"id":"https://openalex.org/keywords/customer-segmentation","display_name":"customer segmentation","score":0.9549999833106995},{"id":"https://openalex.org/keywords/customer-classification","display_name":"customer classification","score":0.703000009059906},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.7649999856948853},{"id":"https://openalex.org/keywords/naive-bayes","display_name":"naive Bayes","score":0.6620000004768372},{"id":"https://openalex.org/keywords/decision-tree","display_name":"decision tree","score":0.8790000081062317},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.9990000128746033},{"id":"https://openalex.org/keywords/sales-forecasting","display_name":"sales forecasting","score":0.6069999933242798},{"id":"https://openalex.org/keywords/marketing-strategy-optimization","display_name":"marketing strategy optimization","score":0.6200000047683716},{"id":"https://openalex.org/keywords/inventory-management","display_name":"inventory management","score":0.996999979019165}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7373999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652999997138977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6428999900817871},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5515000224113464},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5406000018119812},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47130000591278076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4327999949455261},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C127722929","wikidata":"https://www.wikidata.org/wiki/Q7833714","display_name":"Transaction data","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C2984642479","wikidata":"https://www.wikidata.org/wiki/Q7404320","display_name":"Sales forecasting","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.56347/jics.v4i2.303","doi":"https://doi.org/10.56347/jics.v4i2.303","is_oa":true,"landing_page_url":"https://doi.org/10.56347/jics.v4i2.303","pdf_url":"https://journal.kawanad.com/index.php/jics/article/download/303/257","source":{"id":"https://openalex.org/S4387283372","display_name":"Journal Innovations Computer Science","issn_l":"2961-970X","issn":["2961-970X","2961-9718"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal Innovations Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.56347/jics.v4i2.303","doi":"https://doi.org/10.56347/jics.v4i2.303","is_oa":true,"landing_page_url":"https://doi.org/10.56347/jics.v4i2.303","pdf_url":"https://journal.kawanad.com/index.php/jics/article/download/303/257","source":{"id":"https://openalex.org/S4387283372","display_name":"Journal Innovations Computer Science","issn_l":"2961-970X","issn":["2961-970X","2961-9718"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal Innovations Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415564779.pdf","grobid_xml":"https://content.openalex.org/works/W4415564779.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2911964244","https://openalex.org/W3094447026","https://openalex.org/W3128503814","https://openalex.org/W3134081317","https://openalex.org/W3147498416","https://openalex.org/W3159642142","https://openalex.org/W4285102048","https://openalex.org/W4318541481","https://openalex.org/W4323344643","https://openalex.org/W4388430022","https://openalex.org/W4392816148","https://openalex.org/W4401539192","https://openalex.org/W4402381758","https://openalex.org/W4408130217","https://openalex.org/W4408139653","https://openalex.org/W4409777375","https://openalex.org/W4411394284","https://openalex.org/W7215874707"],"related_works":["https://openalex.org/W7125902583","https://openalex.org/W3203086307","https://openalex.org/W7205013924","https://openalex.org/W4211009598","https://openalex.org/W7162556109","https://openalex.org/W4312703273","https://openalex.org/W7072179651","https://openalex.org/W7084408087","https://openalex.org/W4414847400","https://openalex.org/W7219955722"],"abstract_inverted_index":{"In":[0],"the":[1,37,47,72,111,135,164],"evolving":[2],"retail":[3,27,120],"landscape,":[4],"data-driven":[5],"decision-making":[6],"has":[7],"become":[8],"essential":[9],"for":[10,118,148],"understanding":[11],"customer":[12,42,151],"behavior":[13],"and":[14,22,57,81,99,113,129,139,156,169,175,188],"predicting":[15],"sales":[16,28],"trends.":[17],"This":[18],"study":[19,165],"integrates":[20],"clustering":[21,138],"classification":[23,69,104,140],"techniques":[24],"to":[25,184],"analyze":[26],"data":[29,86],"comprising":[30],"1,000":[31],"transactions":[32],"obtained":[33],"from":[34],"Kaggle.":[35],"Using":[36],"K-Means":[38],"algorithm,":[39],"three":[40,76],"optimal":[41],"clusters":[43],"were":[44],"identified":[45],"through":[46],"Elbow":[48],"Method,":[49],"achieving":[50,161],"an":[51],"average":[52],"within-centroid":[53],"distance":[54],"of":[55,61,75,106,115,127,137],"25,272.635":[56],"a":[58,144],"Davies\u2013Bouldin":[59],"Index":[60],"0.443,":[62],"indicating":[63],"clear":[64],"cluster":[65],"separation.":[66],"The":[67,88,131],"subsequent":[68],"phase":[70],"compared":[71],"predictive":[73,189],"performance":[74],"algorithms\u2014Na\u00efve":[77],"Bayes,":[78],"Decision":[79,97],"Tree,":[80],"Random":[82,100],"Forest\u2014on":[83],"70:30":[84],"training-to-testing":[85],"partitions.":[87],"Na\u00efve":[89],"Bayes":[90],"algorithm":[91],"attained":[92],"94.67%":[93],"accuracy,":[94],"while":[95],"both":[96],"Tree":[98],"Forest":[101],"achieved":[102],"perfect":[103],"accuracy":[105,128],"100%.":[107],"These":[108],"findings":[109],"highlight":[110],"robustness":[112],"adaptability":[114],"tree-based":[116],"models":[117],"complex":[119],"datasets,":[121,178],"outperforming":[122],"probabilistic":[123],"methods":[124],"in":[125],"terms":[126],"generalization.":[130],"results":[132],"suggest":[133],"that":[134],"integration":[136],"provides":[141],"retailers":[142],"with":[143],"powerful":[145],"analytical":[146],"framework":[147],"identifying":[149],"high-value":[150],"segments,":[152],"optimizing":[153],"marketing":[154],"strategies,":[155],"enhancing":[157],"inventory":[158],"management.":[159],"Despite":[160],"strong":[162],"outcomes,":[163],"acknowledges":[166],"dataset":[167],"limitations":[168],"recommends":[170],"future":[171],"research":[172],"involving":[173],"larger":[174],"more":[176],"diverse":[177],"as":[179,181],"well":[180],"additional":[182],"features,":[183],"expand":[185],"model":[186],"scalability":[187],"precision.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-28T00:00:00"}