Scribd
Upload
0 views

Final Project Report Format of PBL-1

The project 'Crime Rate Prediction' utilizes machine learning models to forecast crime rates, aiding law enforcement and policymakers in resource allocation and crime prevention. The Random Forest Regressor was identified as the most effective model, demonstrating superior predictive accuracy. Future work includes expanding the dataset and exploring advanced techniques for improved predictions.

Uploaded by

dhairyajain1512
Copyright
© © All Rights Reserved
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
0 views

Final Project Report Format of PBL-1

The project 'Crime Rate Prediction' utilizes machine learning models to forecast crime rates, aiding law enforcement and policymakers in resource allocation and crime prevention. The Random Forest Regressor was identified as the most effective model, demonstrating superior predictive accuracy. Future work includes expanding the dataset and exploring advanced techniques for improved predictions.

Uploaded by

dhairyajain1512
Copyright
© © All Rights Reserved
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 14

Department of Computer Science &

Engineering

Final Project Report

On

Project Title: Crime Rate Prediction

Submitted By Submitted to

Diya Khatri(0905CS231089) CS – B Mr. Yogendra S. Rathore

Devansh Singh Kushwaha(0905CS231077) CS – B

Gopal Namdev(0905CS231099) CS – B (Signature)

Jahanvi Gadkari(0905CS231120) CS - B
Index
1. Abstract of the project
2. Declaration
3. Certificate
4. Implementation of Modules
5. Screenshots of the output
6. Applications of the project
7. Conclusion & Future work
8. References (Books, internet sources etc.)
Abstract
The increasing crime rates pose significant challenges for law enforcement agencies
and policymakers. This project aims to predict crime rates using various machine
learning models, providing a data-driven approach to enhance preventive measures
and resource allocation. We implemented multiple regression models, including
Random Forest Regressor, Decision Tree Regressor, Multi-Layer Perceptron (MLP)
Regressor, Support Vector Machines (SVM), and others. Each model's performance
was evaluated using metrics such as mean squared error, mean absolute error, and
R-squared values. The Random Forest Regressor emerged as the best-performing
model, demonstrating superior predictive accuracy, robustness, and interpretability.
This study underscores the potential of machine learning in enhancing crime rate
prediction, contributing to more informed decision-making processes in crime
prevention and management.
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

DECLARATION

We hereby declare that the Project entitled “Title of project" is our own work conducted
under the supervision of Prof. Guide Name, Department of computer science and
engineering at Institute Of Technology And Management, Gwalior

We further declare that to the best of our knowledge this report does not contain any part
of work that has been submitted for the award of any degree either in this university or in
other university without proper citation.
Diya Khatri 0905CS231089

Devansh Singh Kushwaha 0905CS231077

Gopal Namdev 0905CS231099

Jahanvi Gadkari 0905CS231120

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE

This is to certify that the work embodied in this project entitled “Crime Rate
Prediction" being submitted by Diya Khatri(0905CS231089), Devansh Singh Kushwaha
(0905CS231077), Gopal Namdev(0905CS231099), Jahanvi Gadkari(095CS231120) in
partial fulfillment of the requirement for the award of the degree of the Bachelor of
Technology (Computer Science & Engineering) to Rajiv Gandhi Proudoyogiki
Vishwavidyalaya, Bhopal (M.P.) is a record of Bonafide piece of work, carried out by
them under our supervision and guidance in the Department of computer science and engineering,
Institute Of Technology And Management ,Gwalior(M.P.)

Guided By H.O.D.

(Prof. Guide Name) (Prof. HOD Name)

Assistant Professor Professor

Department of Computer Science Department of Computer Science

ITM, Gwalior (M.P.) ITM, Gwalior (M.P.)

Implementation of Modules
Data Collection and Preprocessing:

 Gathered data from publicly available crime datasets.

 Cleaned and pre-processed data by handling missing values,


normalizing, and encoding categorical variables.

Model Development:

 Implemented various machine learning models: Random Forest


Regressor, Decision Tree Regressor, MLP Regressor, SVM, and
others.

 Performed feature selection to identify relevant features impacting


crime rates.

 Selected a suitable model for the task of prediction.

Model Evaluation:

 Evaluated models using metrics like MSE, MAE, and R-squared


values.
 Random Forest Regressor showed the best performance, with the
lowest MSE and highest R-squared score.

Screenshots of the Output


Data preprocessing steps
Model training process
Evaluation metrics comparison
Predicted crime rates using the Random Forest Regressor
Applications of the Project
 Crime Prevention: Helps law enforcement agencies allocate
resources efficiently by predicting crime hotspots.

 Policy Formulation: Assists policymakers in developing strategies


to reduce crime rates based on predictive insights.

 Urban Planning: Supports urban planners in designing safer


communities by understanding crime trends.

 Public Safety: Enhances public safety through proactive measures


driven by accurate crime rate forecasts.

Conclusion & Future Work


Conclusion:
The Crime Rate Prediction project successfully demonstrates the
potential of machine learning in forecasting crime rates. The
Random Forest Regressor proved to be the most effective model,
providing accurate and robust predictions. This project highlights the
importance of data-driven approaches in crime prevention and
management.

Future Work:
 Expand the dataset to include more features and real-time data
for improved accuracy.

 Explore advanced machine learning techniques like deep learning


for better model performance.

 Develop a user-friendly interface or API for real-time crime rate


prediction.

 Integrate the predictive system with law enforcement databases


for operational use.

References
 Murphy, Kevin P. Machine Learning: A Probalistic Perspective.
Cambridge, Massachusetts: The MIT Press,2012.

 Geron, Aurelien. Hands-On Machine Learning with Scikit-Learn,


Keras, and TensorFlow: Concepts, Tools, and Techniques to Build
Intelligent Systems. 2nd ed. O’Reilly Media, 2019.

 Pandey, Sanjay K., Malu, Siddharth Savyasachi, Machine Learning


with Python: A Hands-On Introduction.

 Online sources:

o Crime Data Portal:


https://www.kaggle.com/datasets/piyush242002/cyber-crime-
in-india-from-2003?resource=download

 Research Papers and Articles:

o Cybercrime: Identification and Prediction Using Machine


Learning Techniques, K. Veena, K. Meena, Ramya Kuppusamy,
Yuvaraja Teekaraman, Ravi V. Angadi, and Amruth Ramesh
Thelkar, 2022.

You might also like