Crime Category Classification in San Francisco using Machine Learning Techniques

Eldho, Jerin (2023) Crime Category Classification in San Francisco using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

This research addresses the challenge of accurately categorizing crime incidents based on textual descriptions, aiming to enhance crime analysis and law enforcement strategies. The study investigates the effectiveness of various machine learning models, including LSTM, GRU, Logistic Regression, SVM, and Random Forest. Through comprehensive evaluation, the Logistic Regression, SVM, and Random Forest models exhibited remarkable accuracy, achieving an average of around 99.91% to 99.97% across categories. This work contributes by showcasing the potential of simpler algorithms in crime categorization tasks, highlighting their reliability and effectiveness. The results are consistent with the state of the art, stressing the importance of customized algorithm selection and feature representation. In reality, these models provide precise crime classification information for better public safety and law enforcement decisions. However, issues in differentiating complicated criminal categories remain, suggesting future study possibilities.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms H Social Sciences > HV Social pathology. Social and public welfare > Criminology Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	22 Nov 2024 10:55
Last Modified:	22 Nov 2024 10:55
URI:	https://norma.ncirl.ie/id/eprint/7184

Actions (login required)

View Item