Predicting Arrest Release Outcomes: A Comparative Analysis of Machine Learning Models

This comparative study evaluates machine learning models for predicting arrest release outcomes using 5,226 marijuana possession cases from the Toronto Police Service (1997-2002). The dataset exhibited significant class imbalance, with only 17.1% detention outcomes versus 82.9% releases. After prepr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:al-Tarbiyah wa-al-ʻilm lil-ʻulūm al-insānīyah : majallah ʻilmīyah muḥakkamah taṣduru ʻan Kullīyat al-Tarbiyah lil-ʻUlūm al-Insānīyah fī Jāmiʻat al-Mawṣil Jg. 34; H. 4; S. 62 - 73
Hauptverfasser: Adebayo, O. P., Ibrahim, Ahmed, Oyeleke, K.T.
Format: Journal Article
Sprache:Arabisch
Englisch
Veröffentlicht: College of Education for Pure Sciences 01.10.2025
Schlagworte:
ISSN:1812-125X, 2664-2530
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This comparative study evaluates machine learning models for predicting arrest release outcomes using 5,226 marijuana possession cases from the Toronto Police Service (1997-2002). The dataset exhibited significant class imbalance, with only 17.1% detention outcomes versus 82.9% releases. After preprocessing to handle missing values and convert categorical variables, we implemented two modeling approaches: a 500-tree Random Forest classifier with feature importance measurement and a binomial Logistic Regression model. Both algorithms demonstrated strong predictive capability for release cases, achieving comparable overall accuracy (83.2-83.4%) and excellent sensitivity (>98%), though they struggled with the critical minority class as evidenced by poor specificity (<7%). The models showed similar discriminative power, with Logistic Regression achieving a marginally higher AUC-ROC (0.733 vs 0.726). Feature importance analysis identified employment status and prior police background checks as the strongest predictors, while demographic factors, including race, also contributed significantly to predictions. These results highlight both the technical challenges of imbalanced classification in justice system data and the ethical considerations surrounding potential algorithmic bias, particularly given the high false positive rate for detention predictions that could exacerbate existing disparities. The study underscores the need for careful model evaluation and responsible implementation when applying predictive analytics to sensitive criminal justice decisions, balancing statistical performance with considerations of fairness and social impact.
AbstractList This comparative study evaluates machine learning models for predicting arrest release outcomes using 5,226 marijuana possession cases from the Toronto Police Service (1997-2002). The dataset exhibited significant class imbalance, with only 17.1% detention outcomes versus 82.9% releases. After preprocessing to handle missing values and convert categorical variables, we implemented two modeling approaches: a 500-tree Random Forest classifier with feature importance measurement and a binomial Logistic Regression model. Both algorithms demonstrated strong predictive capability for release cases, achieving comparable overall accuracy (83.2-83.4%) and excellent sensitivity (>98%), though they struggled with the critical minority class as evidenced by poor specificity (<7%). The models showed similar discriminative power, with Logistic Regression achieving a marginally higher AUC-ROC (0.733 vs 0.726). Feature importance analysis identified employment status and prior police background checks as the strongest predictors, while demographic factors, including race, also contributed significantly to predictions. These results highlight both the technical challenges of imbalanced classification in justice system data and the ethical considerations surrounding potential algorithmic bias, particularly given the high false positive rate for detention predictions that could exacerbate existing disparities. The study underscores the need for careful model evaluation and responsible implementation when applying predictive analytics to sensitive criminal justice decisions, balancing statistical performance with considerations of fairness and social impact.
Author Adebayo, O. P.
Oyeleke, K.T.
Ibrahim, Ahmed
Author_xml – sequence: 1
  givenname: O. P.
  surname: Adebayo
  fullname: Adebayo, O. P.
– sequence: 2
  givenname: Ahmed
  surname: Ibrahim
  fullname: Ibrahim, Ahmed
– sequence: 3
  givenname: K.T.
  surname: Oyeleke
  fullname: Oyeleke, K.T.
BookMark eNo90E1LAzEUheEgClbt3mX-wNSbycck7krxo1BRxIK7cCe9oynTiSSj4L9Xq7g6cBbP4j1hh0MaiLFzATMprXMXWyqzD6mimilnGjhgk9oYVdVawiGbCCvqStT6-ZhNS9kCQG0bqRozYeuHTJsYxji88HnOVEb-SD1hIX7_Poa0o3LJ53yRdm-YcYwfxOcD9p8lFp46fofhNQ7EV4R5-DHu0ob6csaOOuwLTf_2lK2vr54Wt9Xq_ma5mK-qIJSDilrYiNaYYIKuLWgDBlpllQThsDVonFbYCS3QKEnYtU4LQKWss7JGi_KULX_dTcKtf8txh_nTJ4x-f6T84jGPMfTkja2FaBog0ZKSnWllB62DRmFAoaX-tuDXCjmVkqn79wT4fWX_XdnvK_t9ZfkFnARxRw
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.33899/jes.v34i4.49670
DatabaseName CrossRef
Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2664-2530
EndPage 73
ExternalDocumentID oai_doaj_org_article_68211770e1be43f6b3f0b9074aca1535
10_33899_jes_v34i4_49670
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
ID FETCH-LOGICAL-c1490-eb0d1b66c6c528056060b4843019ab6a6954af151a643eafb9510a4489832a8a3
IEDL.DBID DOA
ISSN 1812-125X
IngestDate Tue Oct 07 09:25:13 EDT 2025
Thu Oct 09 00:12:52 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Language Arabic
English
License https://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1490-eb0d1b66c6c528056060b4843019ab6a6954af151a643eafb9510a4489832a8a3
OpenAccessLink https://doaj.org/article/68211770e1be43f6b3f0b9074aca1535
PageCount 12
ParticipantIDs doaj_primary_oai_doaj_org_article_68211770e1be43f6b3f0b9074aca1535
crossref_primary_10_33899_jes_v34i4_49670
PublicationCentury 2000
PublicationDate 2025-10-01
PublicationDateYYYYMMDD 2025-10-01
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-01
  day: 01
PublicationDecade 2020
PublicationTitle al-Tarbiyah wa-al-ʻilm lil-ʻulūm al-insānīyah : majallah ʻilmīyah muḥakkamah taṣduru ʻan Kullīyat al-Tarbiyah lil-ʻUlūm al-Insānīyah fī Jāmiʻat al-Mawṣil
PublicationYear 2025
Publisher College of Education for Pure Sciences
Publisher_xml – name: College of Education for Pure Sciences
SSID ssj0002873476
Score 2.3047166
Snippet This comparative study evaluates machine learning models for predicting arrest release outcomes using 5,226 marijuana possession cases from the Toronto Police...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 62
SubjectTerms bail decision prediction
bias and fairness in ml
classification algorithms
comparative analysis
predicting
Title Predicting Arrest Release Outcomes: A Comparative Analysis of Machine Learning Models
URI https://doaj.org/article/68211770e1be43f6b3f0b9074aca1535
Volume 34
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2664-2530
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002873476
  issn: 1812-125X
  databaseCode: DOA
  dateStart: 20050101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwFLRQxcCCQIAoX_LAwmDqxI5rs5WKigFKhajULbIdG7VCbZV-_H6enRSysbAmURTds3Xv4qc7hG699txIqghIBU14IhWRBS-IMjbTjKVeVSauL93hUE4matSI-gozYZU9cAVcR8g0nCtSlxjHmReGeWqCotNWw26N7qXQ9TTE1Cz-MuoyHpPlAoMRYPFJdUbJgp9cZwYidMv4lN9zJUJOcYOTGtb9kWMGR-iwbg5xr_qoY7SnyxM0HpXhMCWMJ8OdEKWB34ErgH3w22YNC8atHnAP939tvPHOaQQvPH6N05IO10aqnzikn32tTtF48PTRfyZ1GAKxIGIocYYWiRHCCpulEtoWKqjhksMGVdoILVTGtQf-1tBjOO1NaJ00iC8Fe1ZLzc5Qa76Yu3OEnWWJTXyqvSo4tYVJXeayzHsroZ6SttHdDo58WXle5KAVInQ5QJdH6PIIXRs9Brx-ngtu1fEC1DCva5j_VcOL_3jJJTpIQzZvHLS7Qq11uXHXaN9u19NVeROXxzcVzryg
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Predicting+Arrest+Release+Outcomes%3A+A+Comparative+Analysis+of+Machine+Learning+Models&rft.jtitle=al-Tarbiyah+wa-al-%CA%BBilm+lil-%CA%BBul%C5%ABm+al-ins%C4%81n%C4%AByah+%3A+majallah+%CA%BBilm%C4%AByah+mu%E1%B8%A5akkamah+ta%E1%B9%A3duru+%CA%BBan+Kull%C4%AByat+al-Tarbiyah+lil-%CA%BBUl%C5%ABm+al-Ins%C4%81n%C4%AByah+f%C4%AB+J%C4%81mi%CA%BBat+al-Maw%E1%B9%A3il&rft.au=O.+P.+Adebayo&rft.au=Ahmed+Ibrahim&rft.au=K.T.+Oyeleke&rft.date=2025-10-01&rft.pub=College+of+Education+for+Pure+Sciences&rft.issn=1812-125X&rft.eissn=2664-2530&rft.volume=34&rft.issue=4&rft.spage=62&rft.epage=73&rft_id=info:doi/10.33899%2Fjes.v34i4.49670&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_68211770e1be43f6b3f0b9074aca1535
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1812-125X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1812-125X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1812-125X&client=summon