{"id":"https://openalex.org/W4390577421","doi":"https://doi.org/10.4018/979-8-3693-0413-6.ch006","title":"Big Data Preprocessing, Techniques, Integration, Transformation, Normalisation, Cleaning, Discretization, and Binning","display_name":"Big Data Preprocessing, Techniques, Integration, Transformation, Normalisation, Cleaning, Discretization, and Binning","publication_year":2024,"publication_date":"2024-01-04","ids":{"openalex":"https://openalex.org/W4390577421","doi":"https://doi.org/10.4018/979-8-3693-0413-6.ch006"},"language":"en","primary_location":{"id":"doi:10.4018/979-8-3693-0413-6.ch006","doi":"https://doi.org/10.4018/979-8-3693-0413-6.ch006","is_oa":false,"landing_page_url":"https://doi.org/10.4018/979-8-3693-0413-6.ch006","pdf_url":null,"source":{"id":"https://openalex.org/S4210225011","display_name":"Advances in business information systems and analytics book series","issn_l":"2327-3275","issn":["2327-3275","2327-3283"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Business Information Systems and Analytics","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W4390577585","display_name":"Big Data Analytics Techniques for Market Intelligence"},"type":"book-chapter","is_traditional":true,"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/A5053558643","display_name":"Pranali Dhawas","orcid":"https://orcid.org/0009-0003-4276-2310","observed_orcids":["https://orcid.org/0009-0003-4276-2310"]},"institutions":[{"id":"https://openalex.org/I4210146358","display_name":"Raisoni Group of Institutions","ror":"https://ror.org/03dp11s58","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210146358"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranali Dhawas","raw_affiliation_strings":["G.H. Raisoni College of Engineering, Nagpur, India"],"raw_orcid":"https://orcid.org/0009-0003-4276-2310","affiliations":[{"raw_affiliation_string":"G.H. Raisoni College of Engineering, Nagpur, India","institution_ids":["https://openalex.org/I4210146358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092647281","display_name":"Abhishek M. Dhore","orcid":"https://orcid.org/0000-0001-7620-442X","observed_orcids":["https://orcid.org/0000-0001-7620-442X"]},"institutions":[{"id":"https://openalex.org/I4210162439","display_name":"MIT Art, Design and Technology University","ror":"https://ror.org/05b69xa56","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210162439"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhishek Dhore","raw_affiliation_strings":["MIT School of Computing, MIT ADT University, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT School of Computing, MIT ADT University, Pune, India","institution_ids":["https://openalex.org/I4210162439"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035828428","display_name":"Dhananjay Abhilash Bhagat","orcid":"https://orcid.org/0009-0009-1100-3219","observed_orcids":["https://orcid.org/0009-0009-1100-3219"]},"institutions":[{"id":"https://openalex.org/I4210146358","display_name":"Raisoni Group of Institutions","ror":"https://ror.org/03dp11s58","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210146358"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhananjay Bhagat","raw_affiliation_strings":["G.H. Raisoni College of Engineering, Nagpur, India"],"raw_orcid":"https://orcid.org/0009-0009-1100-3219","affiliations":[{"raw_affiliation_string":"G.H. Raisoni College of Engineering, Nagpur, India","institution_ids":["https://openalex.org/I4210146358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108891412","display_name":"Ritu Dorlikar Pawar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210146358","display_name":"Raisoni Group of Institutions","ror":"https://ror.org/03dp11s58","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210146358"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ritu Dorlikar Pawar","raw_affiliation_strings":["G.H. Raisoni College of Engineering, Nagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"G.H. Raisoni College of Engineering, Nagpur, India","institution_ids":["https://openalex.org/I4210146358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093647279","display_name":"Ashwini Kukade","orcid":"https://orcid.org/0009-0007-6185-6389","observed_orcids":["https://orcid.org/0009-0007-6185-6389"]},"institutions":[{"id":"https://openalex.org/I4210146358","display_name":"Raisoni Group of Institutions","ror":"https://ror.org/03dp11s58","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210146358"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashwini Kukade","raw_affiliation_strings":["G.H. Raisoni College of Engineering, Nagpur, India"],"raw_orcid":"https://orcid.org/0009-0007-6185-6389","affiliations":[{"raw_affiliation_string":"G.H. Raisoni College of Engineering, Nagpur, India","institution_ids":["https://openalex.org/I4210146358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049681996","display_name":"Kamlesh Kalbande","orcid":"https://orcid.org/0000-0003-2705-1732","observed_orcids":["https://orcid.org/0000-0003-2705-1732"]},"institutions":[{"id":"https://openalex.org/I4210146358","display_name":"Raisoni Group of Institutions","ror":"https://ror.org/03dp11s58","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210146358"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kamlesh Kalbande","raw_affiliation_strings":["G.H. Raisoni College of Engineering, Nagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"G.H. Raisoni College of Engineering, Nagpur, India","institution_ids":["https://openalex.org/I4210146358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":27.3758,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.99657937,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8784000277519226,"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/T11719","display_name":"Data Quality and Management","score":0.8784000277519226,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.11469999700784683,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0005000000237487257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data-preprocessing","display_name":"big data preprocessing","score":0.9890000224113464},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.972000002861023},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.9810000061988831},{"id":"https://openalex.org/keywords/data-transformation","display_name":"data transformation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/data-normalization","display_name":"data normalization","score":0.7409999966621399},{"id":"https://openalex.org/keywords/discretization","display_name":"discretization","score":0.9649999737739563},{"id":"https://openalex.org/keywords/data-binning","display_name":"binning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"unstructured data","score":0.7289999723434448}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8394021987915039},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7515569925308228},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7453237771987915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357339859008789},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.71612149477005},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6895437240600586},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6045436859130859},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5572401881217957},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5136784911155701},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.49225202202796936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46165239810943604},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.456923246383667},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.41828659176826477},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4170551300048828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14449438452720642},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.11457973718643188},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4018/979-8-3693-0413-6.ch006","doi":"https://doi.org/10.4018/979-8-3693-0413-6.ch006","is_oa":false,"landing_page_url":"https://doi.org/10.4018/979-8-3693-0413-6.ch006","pdf_url":null,"source":{"id":"https://openalex.org/S4210225011","display_name":"Advances in business information systems and analytics book series","issn_l":"2327-3275","issn":["2327-3275","2327-3283"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Business Information Systems and Analytics","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2981372033","https://openalex.org/W2982674075","https://openalex.org/W2991159430","https://openalex.org/W2993259699","https://openalex.org/W3119025276","https://openalex.org/W3132196880","https://openalex.org/W3161185138","https://openalex.org/W4220726286","https://openalex.org/W4309229256","https://openalex.org/W4318539077"],"related_works":["https://openalex.org/W7133203895","https://openalex.org/W4399687785","https://openalex.org/W2906371607","https://openalex.org/W2621914863","https://openalex.org/W3111905479","https://openalex.org/W4386456560","https://openalex.org/W7066369132","https://openalex.org/W2614290080","https://openalex.org/W3173272200","https://openalex.org/W3164045371"],"abstract_inverted_index":{"\u201cUnleashing":[0],"the":[1,19,43,55],"Power":[2],"of":[3,22,57],"Big":[4],"Data:":[5],"Innovative":[6],"Approaches":[7],"to":[8,32,92],"Preprocessing":[9],"for":[10,59,86],"Enhanced":[11],"Analytics\u201d":[12],"is":[13,82],"a":[14,38,83],"groundbreaking":[15],"chapter":[16,53,81],"that":[17],"explores":[18],"pivotal":[20],"role":[21],"preprocessing":[23,58],"in":[24],"big":[25,101],"data":[26,36,47,64,73,94],"analytics.":[27],"It":[28],"introduces":[29],"diverse":[30],"techniques":[31],"transform":[33],"raw,":[34],"unstructured":[35],"into":[37],"clean,":[39],"analyzable":[40],"format,":[41],"addressing":[42],"challenges":[44],"posed":[45],"by":[46],"volume,":[48],"velocity,":[49],"and":[50,67,70,77,88,96],"variety.":[51],"The":[52],"emphasizes":[54],"significance":[56],"accurate":[60],"outcomes,":[61],"covers":[62],"advanced":[63],"cleaning,":[65],"integration,":[66],"transformation":[68],"techniques,":[69],"discusses":[71],"real-time":[72],"preprocessing,":[74],"emerging":[75],"technologies,":[76],"future":[78],"directions.":[79],"This":[80],"comprehensive":[84],"resource":[85],"researchers":[87],"practitioners,":[89],"enabling":[90],"them":[91],"enhance":[93],"analytics":[95],"derive":[97],"valuable":[98],"insights":[99],"from":[100],"data.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-01-05T00:00:00"}
