Comparing regression models to predict property crime in high-risk Lima districts

Maria Escobedo; Cynthia Tapia; Juan Gutierrez; Victor Ayma

doi:10.14569/IJACSA.2024.0150307

Comparing regression models to predict property crime in high-risk Lima districts

Maria Escobedo
, Cynthia Tapia
, Juan Gutierrez
, Victor Ayma

Research output: Contribution to journal › Article in a journal › peer-review

1 Scopus citations

Abstract

Crime continues to be an issue, in Metropolitan Lima, Peru affecting society. Our focus is on property crimes. We recognized the lack of studies on predicting these crimes. To tackle this problem, we used regression techniques such as XGBoost, Extra Tree, Support Vector, Bagging, Random Forest and AdaBoost. Through GridsearchCV we optimized hyperparameters to enhance our research findings. The results showed that Extra Tree Regression stood out as the model with an R2 value of 0.79. Additionally, error metrics like MSE (185.43) RMSE (13.62) and MAE (10.47) were considered to evaluate the model's performance. Our approach considers time patterns in crime incidents. Contributes, to addressing the issue of insecurity in a meaningful way.

Original language	English
Pages (from-to)	62-68
Number of pages	7
Journal	International Journal of Advanced Computer Science and Applications
Volume	15
Issue number	3
DOIs	https://doi.org/10.14569/IJACSA.2024.0150307
State	Published - 2024

Bibliographical note

Publisher Copyright:
© (2024), (Science and Information Organization). All Rights Reserved.

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure
SDG 16 Peace, Justice and Strong Institutions
SDG 17 Partnerships for the Goals

Keywords

crime
machine learning
prediction
regression
Supervised techniques

Access to Document

10.14569/IJACSA.2024.0150307

Cite this

@article{be7aee1e005544bbbfb6c337bcbdc3ae,

title = "Comparing regression models to predict property crime in high-risk Lima districts",

abstract = "Crime continues to be an issue, in Metropolitan Lima, Peru affecting society. Our focus is on property crimes. We recognized the lack of studies on predicting these crimes. To tackle this problem, we used regression techniques such as XGBoost, Extra Tree, Support Vector, Bagging, Random Forest and AdaBoost. Through GridsearchCV we optimized hyperparameters to enhance our research findings. The results showed that Extra Tree Regression stood out as the model with an R2 value of 0.79. Additionally, error metrics like MSE (185.43) RMSE (13.62) and MAE (10.47) were considered to evaluate the model's performance. Our approach considers time patterns in crime incidents. Contributes, to addressing the issue of insecurity in a meaningful way.",

keywords = "crime, machine learning, prediction, regression, Supervised techniques, T{\'e}cnicas supervisadas, Aprendizaje autom{\'a}tico, Regresi{\'o}n, Crimen, Predicci{\'o}n",

author = "Maria Escobedo and Cynthia Tapia and Juan Gutierrez and Victor Ayma",

year = "2024",

doi = "10.14569/IJACSA.2024.0150307",

language = "English",

volume = "15",

pages = "62--68",

journal = "International Journal of Advanced Computer Science and Applications",

issn = "2158-107X",

publisher = "Science and Information Organization",

number = "3",

}

TY - JOUR

T1 - Comparing regression models to predict property crime in high-risk Lima districts

AU - Escobedo, Maria

AU - Tapia, Cynthia

AU - Gutierrez, Juan

AU - Ayma, Victor

PY - 2024

Y1 - 2024

N2 - Crime continues to be an issue, in Metropolitan Lima, Peru affecting society. Our focus is on property crimes. We recognized the lack of studies on predicting these crimes. To tackle this problem, we used regression techniques such as XGBoost, Extra Tree, Support Vector, Bagging, Random Forest and AdaBoost. Through GridsearchCV we optimized hyperparameters to enhance our research findings. The results showed that Extra Tree Regression stood out as the model with an R2 value of 0.79. Additionally, error metrics like MSE (185.43) RMSE (13.62) and MAE (10.47) were considered to evaluate the model's performance. Our approach considers time patterns in crime incidents. Contributes, to addressing the issue of insecurity in a meaningful way.

AB - Crime continues to be an issue, in Metropolitan Lima, Peru affecting society. Our focus is on property crimes. We recognized the lack of studies on predicting these crimes. To tackle this problem, we used regression techniques such as XGBoost, Extra Tree, Support Vector, Bagging, Random Forest and AdaBoost. Through GridsearchCV we optimized hyperparameters to enhance our research findings. The results showed that Extra Tree Regression stood out as the model with an R2 value of 0.79. Additionally, error metrics like MSE (185.43) RMSE (13.62) and MAE (10.47) were considered to evaluate the model's performance. Our approach considers time patterns in crime incidents. Contributes, to addressing the issue of insecurity in a meaningful way.

KW - crime

KW - machine learning

KW - prediction

KW - regression

KW - Supervised techniques

KW - Técnicas supervisadas

KW - Aprendizaje automático

KW - Regresión

KW - Crimen

KW - Predicción

UR - https://www.scopus.com/pages/publications/85189935904

UR - https://www.mendeley.com/catalogue/88eb8922-7eef-3587-9df7-394a9b6fd5c3/

UR - https://hdl.handle.net/20.500.14139/EC9JNP

U2 - 10.14569/IJACSA.2024.0150307

DO - 10.14569/IJACSA.2024.0150307

M3 - Article in a journal

AN - SCOPUS:85189935904

SN - 2158-107X

VL - 15

SP - 62

EP - 68

JO - International Journal of Advanced Computer Science and Applications

JF - International Journal of Advanced Computer Science and Applications

IS - 3

ER -

Comparing regression models to predict property crime in high-risk Lima districts

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this