{"id":"https://openalex.org/W7224096800","doi":"https://doi.org/10.6084/m9.figshare.34823334","title":"Data Science Salary Prediction: A Comparative Study of Standard Regressors and Leakage Testing","display_name":"Data Science Salary Prediction: A Comparative Study of Standard Regressors and Leakage Testing","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224096800","doi":"https://doi.org/10.6084/m9.figshare.34823334"},"language":"en","primary_location":{"id":"doi:10.6084/m9.figshare.34823334","doi":"https://doi.org/10.6084/m9.figshare.34823334","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34823334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.6084/m9.figshare.34823334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151584446","display_name":"Sareena Bilal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sareena Bilal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5151584446"],"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.5859000086784363,"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":0.5859000086784363,"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/T13812","display_name":"AI and HR Technologies","score":0.12809999287128448,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"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/T13141","display_name":"Statistical Methods and Applications","score":0.08079999685287476,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/salary-prediction","display_name":"salary prediction","score":0.9430000185966492},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.8169999718666077},{"id":"https://openalex.org/keywords/target-leakage","display_name":"target leakage","score":0.8199999928474426},{"id":"https://openalex.org/keywords/regression-models","display_name":"regression models","score":0.9010000228881836},{"id":"https://openalex.org/keywords/occupational-titles","display_name":"job titles","score":0.36500000953674316},{"id":"https://openalex.org/keywords/experience-level","display_name":"experience level","score":0.6769999861717224},{"id":"https://openalex.org/keywords/employment-type","display_name":"employment type","score":0.5460000038146973},{"id":"https://openalex.org/keywords/firm-size","display_name":"firm size","score":0.621999979019165}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7382000088691711},{"id":"https://openalex.org/C2780090960","wikidata":"https://www.wikidata.org/wiki/Q194489","display_name":"Salary","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5331000089645386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5202999711036682},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.6084/m9.figshare.34823334","doi":"https://doi.org/10.6084/m9.figshare.34823334","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34823334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.6084/m9.figshare.34823334.v1","doi":"https://doi.org/10.6084/m9.figshare.34823334.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34823334.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.6084/m9.figshare.34823334","doi":"https://doi.org/10.6084/m9.figshare.34823334","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34823334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7578999996185303}],"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/W7112439191","https://openalex.org/W4404790908","https://openalex.org/W7220539175","https://openalex.org/W4411612709","https://openalex.org/W4389200069","https://openalex.org/W7171850441","https://openalex.org/W4416233890","https://openalex.org/W7162285191","https://openalex.org/W4393103029","https://openalex.org/W4377822572"],"abstract_inverted_index":{"This":[0],"study":[1,95,147],"presents":[2],"a":[3,16,162],"comparative":[4],"analysis":[5,139],"of":[6,28,77,114,123,131,140],"standard":[7,124],"regression":[8],"models":[9,83],"for":[10,23,91,116],"predicting":[11],"data":[12,24,33,40,73,132],"science":[13,41],"salaries,":[14],"with":[15,172],"specific":[17],"focus":[18],"on":[19],"identifying":[20],"and":[21,63,80,106,144,181,189],"testing":[22],"leakage\u2014a":[25],"frequent":[26],"cause":[27],"over-optimistic":[29],"results":[30],"in":[31,134],"applied":[32],"mining.The":[34],"dataset":[35,99],"comprises":[36],"3,761":[37],"records":[38],"describing":[39],"positions,":[42,108],"featuring":[43],"variables":[44],"such":[45,178,184],"as":[46,179,185],"work":[47],"year,":[48],"experience":[49],"level":[50],"(entry,":[51],"mid,":[52],"senior,":[53,104],"executive),":[54],"employment":[55],"type,":[56],"job":[57,156],"title,":[58],"company":[59,61],"location,":[60],"size,":[62],"salary":[64],"converted":[65],"to":[66,88,165],"US":[67],"dollars.The":[68],"methodology":[69],"involves":[70],"preprocessing":[71],"the":[72,82,98,112,135,141,166],"through":[74],"one-hot":[75],"encoding":[76],"categorical":[78],"features":[79,183],"evaluating":[81,174],"under":[84],"different":[85],"experimental":[86],"settings":[87],"explicitly":[89],"test":[90],"target":[92,168],"leakage.":[93],"The":[94],"highlights":[96],"that":[97],"is":[100],"heavily":[101],"skewed":[102,167],"toward":[103],"full-time,":[105],"US-based":[107],"which":[109,152],"may":[110],"affect":[111],"reliability":[113],"predictions":[115],"other":[117],"demographics.Key":[118],"contributions":[119],"include:A":[120],"side-by-side":[121],"comparison":[122],"regressors":[125],"using":[126],"default":[127],"hyperparameters.An":[128],"explicit":[129],"evaluation":[130],"leakage":[133],"prediction":[136],"pipeline.An":[137],"exploratory":[138],"dataset's":[142],"characteristics":[143],"feature":[145],"distributions.The":[146],"also":[148],"outlines":[149],"future":[150],"work,":[151],"includes":[153],"grouping":[154],"similar":[155],"titles":[157],"into":[158],"role":[159],"families,":[160],"applying":[161],"log":[163],"transformation":[164],"variable,":[169],"tuning":[170],"hyperparameters":[171],"cross-validation,":[173],"gradient":[175],"boosting":[176],"libraries":[177],"XGBoost,":[180],"adding":[182],"remote-work":[186],"ratio,":[187],"industry,":[188],"required":[190],"skills.":[191]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}