Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends

Meghna Halder; Payal Sinha; Digonto Biswas; Tiansheng Yang; Rajkumar Singh Rathore

doi:10.1007/978-981-96-8104-4_27

Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends

Meghna Halder
, Payal Sinha
, Digonto Biswas
, Tiansheng Yang^*
, Rajkumar Singh Rathore

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This research paper aims to improve public safety through the use of crime prediction and its analysis. This research predicts crime hotspots across the country by applying various classifiers such as, Gradient Boosting, Decision Tree, Random Forest, and Support Vector Machine. Data augmentation methods like scaling and SMOTE has been used to help balance class distribution and increase accuracy. Support Vector Machine obtains an accuracy value of 0.96 in our model when SMOTE and feature scaling are used together. This machine learning model provides the particular pattern to predict future crimes which ultimately helps the law enforcement to make the society safe and free of crimes.

Original language	English
Title of host publication	Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025
Editors	Abhishek Swaroop, Vineet Kansal, Aboul Ella Hassanien
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	419-433
Number of pages	15
ISBN (Print)	9789819681037
DOIs	https://doi.org/10.1007/978-981-96-8104-4_27
Publication status	Published - 15 Jan 2026
Event	6th Doctoral Symposium on Computational Intelligence, DoSCI 2025 - Lucknow, Hybrid, India Duration: 28 Mar 2025 → 29 Mar 2025

Publication series

Name	Lecture Notes in Networks and Systems
Volume	1498 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	6th Doctoral Symposium on Computational Intelligence, DoSCI 2025
Country/Territory	India
City	Lucknow, Hybrid
Period	28/03/25 → 29/03/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 16 Peace, Justice and Strong Institutions

Keywords

Crime prediction
Decision tree
Feature scaling
Gradient boosting
Public safety
Random forest
SMOTE
Support vector machine

Access to Document

10.1007/978-981-96-8104-4_27

Cite this

Halder, M., Sinha, P., Biswas, D., Yang, T., & Rathore, R. S. (2026). Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends. In A. Swaroop, V. Kansal, & A. E. Hassanien (Eds.), Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025 (pp. 419-433). (Lecture Notes in Networks and Systems; Vol. 1498 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-8104-4_27

Halder, Meghna ; Sinha, Payal ; Biswas, Digonto et al. / Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends. Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025. editor / Abhishek Swaroop ; Vineet Kansal ; Aboul Ella Hassanien. Springer Science and Business Media Deutschland GmbH, 2026. pp. 419-433 (Lecture Notes in Networks and Systems).

@inproceedings{3d6103c862f244559206d305a86cbc49,

title = "Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends",

abstract = "This research paper aims to improve public safety through the use of crime prediction and its analysis. This research predicts crime hotspots across the country by applying various classifiers such as, Gradient Boosting, Decision Tree, Random Forest, and Support Vector Machine. Data augmentation methods like scaling and SMOTE has been used to help balance class distribution and increase accuracy. Support Vector Machine obtains an accuracy value of 0.96 in our model when SMOTE and feature scaling are used together. This machine learning model provides the particular pattern to predict future crimes which ultimately helps the law enforcement to make the society safe and free of crimes.",

keywords = "Crime prediction, Decision tree, Feature scaling, Gradient boosting, Public safety, Random forest, SMOTE, Support vector machine",

author = "Meghna Halder and Payal Sinha and Digonto Biswas and Tiansheng Yang and Rathore, \{Rajkumar Singh\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 6th Doctoral Symposium on Computational Intelligence, DoSCI 2025 ; Conference date: 28-03-2025 Through 29-03-2025",

year = "2026",

month = jan,

day = "15",

doi = "10.1007/978-981-96-8104-4\_27",

language = "English",

isbn = "9789819681037",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "419--433",

editor = "Abhishek Swaroop and Vineet Kansal and Hassanien, \{Aboul Ella\}",

booktitle = "Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025",

}

Halder, M, Sinha, P, Biswas, D, Yang, T & Rathore, RS 2026, Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends. in A Swaroop, V Kansal & AE Hassanien (eds), Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025. Lecture Notes in Networks and Systems, vol. 1498 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 419-433, 6th Doctoral Symposium on Computational Intelligence, DoSCI 2025, Lucknow, Hybrid, India, 28/03/25. https://doi.org/10.1007/978-981-96-8104-4_27

Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends. / Halder, Meghna; Sinha, Payal; Biswas, Digonto et al.
Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025. ed. / Abhishek Swaroop; Vineet Kansal; Aboul Ella Hassanien. Springer Science and Business Media Deutschland GmbH, 2026. p. 419-433 (Lecture Notes in Networks and Systems; Vol. 1498 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends

AU - Halder, Meghna

AU - Sinha, Payal

AU - Biswas, Digonto

AU - Yang, Tiansheng

AU - Rathore, Rajkumar Singh

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026/1/15

Y1 - 2026/1/15

N2 - This research paper aims to improve public safety through the use of crime prediction and its analysis. This research predicts crime hotspots across the country by applying various classifiers such as, Gradient Boosting, Decision Tree, Random Forest, and Support Vector Machine. Data augmentation methods like scaling and SMOTE has been used to help balance class distribution and increase accuracy. Support Vector Machine obtains an accuracy value of 0.96 in our model when SMOTE and feature scaling are used together. This machine learning model provides the particular pattern to predict future crimes which ultimately helps the law enforcement to make the society safe and free of crimes.

AB - This research paper aims to improve public safety through the use of crime prediction and its analysis. This research predicts crime hotspots across the country by applying various classifiers such as, Gradient Boosting, Decision Tree, Random Forest, and Support Vector Machine. Data augmentation methods like scaling and SMOTE has been used to help balance class distribution and increase accuracy. Support Vector Machine obtains an accuracy value of 0.96 in our model when SMOTE and feature scaling are used together. This machine learning model provides the particular pattern to predict future crimes which ultimately helps the law enforcement to make the society safe and free of crimes.

KW - Crime prediction

KW - Decision tree

KW - Feature scaling

KW - Gradient boosting

KW - Public safety

KW - Random forest

KW - SMOTE

KW - Support vector machine

UR - https://www.scopus.com/pages/publications/105028789358

U2 - 10.1007/978-981-96-8104-4_27

DO - 10.1007/978-981-96-8104-4_27

M3 - Conference contribution

AN - SCOPUS:105028789358

SN - 9789819681037

T3 - Lecture Notes in Networks and Systems

SP - 419

EP - 433

BT - Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025

A2 - Swaroop, Abhishek

A2 - Kansal, Vineet

A2 - Hassanien, Aboul Ella

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th Doctoral Symposium on Computational Intelligence, DoSCI 2025

Y2 - 28 March 2025 through 29 March 2025

ER -

Halder M, Sinha P, Biswas D, Yang T, Rathore RS. Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends. In Swaroop A, Kansal V, Hassanien AE, editors, Proceedings of 6th Doctoral Symposium on Computational Intelligence - DoSCI 2025. Springer Science and Business Media Deutschland GmbH. 2026. p. 419-433. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-96-8104-4_27

Deployment of Machine Learning Model for Predictive Analysis of Rising Crime Trends

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Cite this