Journal of Artificial Intelligence and Big Data, 2021, 1, 1334
www.scipublications.com/journal/index.php/jaibd
DOI: 10.31586/jaibd.2021.1334
DOI: https://doi.org/10.31586/jaibd.2021.1334 Journal of Artificial Intelligence and Big Data
Article
An Analysis of Crime Prediction and Classification Using Data
Mining Techniques
Anuj Kumar Gupta
1,*
, Dheeraj Varun Kumar Reddy Buddula
2
, Hari Hara Sudheer Patchipulusu
3
, Achuthananda
Reddy Polu
4
, Bhumeka Narra
5
, Navya Vattikonda
6
1
Oracle ERP Senior Business Analyst, Genesis Alkali, USA
2
Software Engineer, Anthem Inc, USA
3
Software Engineer, Iheartmedia, USA
4
SDE3, Goldman Sachs, USA
5
Sr Java Developer, Statefarm, USA
6
Business Intelligence Engineer, International Medical Group Inc, USA
*Correspondence: Anuj Kumar Gupta
Abstract: Crime is a serious and widespread problem in their society, thus preventing it is essential.
Assignment. A significant number of crimes are committed every day. One tool for dealing with
model crime is data mining. Crimes are costly to society in many ways, and they are also a major
source of frustration for its members. A major area of machine learning research is crime detection.
This paper analyzes crime prediction and classification using data mining techniques on a crime
dataset spanning 2006 to 2016. This approach begins with cleaning and extracting features from raw
data for data preparation. Then, machine learning and deep learning models, including RNN-LSTM,
ARIMA, and Linear Regression, are applied. The performance of these models is evaluated using
metrics like Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The
RNN-LSTM model achieved the lowest RMSE of 18.42, demonstrating superior predictive accuracy
among the evaluated models. Data visualization techniques further unveiled crime patterns,
offering actionable insights to prevent crime.
Keywords: Crime Prediction, Crime Data, Data Mining Visualization, Machine Learning, Deep
Learning
1. Introduction
Crime poses a significant threat to society, and addressing it effectively has become
increasingly complex due to its non-systematic and non-random nature. Modern
technologies have not only advanced crime-solving methods but have also empowered
criminals to carry out sophisticated offenses. According to the Crime Records Bureau,
while some crimes, such as burglary and arson, have decreased, others, including murder,
sexual abuse, and gang rape, have shown a significant rise [1]. Understanding the
probability of crime in specific hotspot locations is crucial for devising effective
preventive measures.
Crimes occur at various scales, from small villages to major urban centers, and they
encompass a wide range of offenses such as murder, kidnapping, robbery, rape, assault,
and more. Rising crime rates increase the urgency for law enforcement to address and
resolve cases efficiently [2]. Predictive policing, which utilizes analytical and predictive
techniques to identify potential crimes, has proven effective. However, as the crime rate
increases and criminals become more technologically advanced, manual analysis of crime
data stored in large warehouses becomes impractical. This necessitates the adoption of
How to cite this paper:
Gupta, A. K., Reddy Buddula, D. V.
K., Patchipulusu, H. H. S., Polu, A.
R., Narra, B., & Vattikonda, N.
(2021). An Analysis of Crime Predic-
tion and Classification Using Data
Mining Techniques. Journal of Artifi-
cial Intelligence and Big Data, 1(1),
156–166.
DOI: 10.31586/jaibd.2021.1334
Received: August 22, 2021
Revised: November 26, 2021
Accepted: December 23, 2021
Published: December 27, 2021
Copyright: © 2021 by the authors.
Submitted for possible open access
publication under the terms and
conditions of the Creative Commons
Attribution (CC BY) license
(http://creativecommons.org/licenses
/by/4.0/).