CeaseCrime: Utilizing Machine Learning to Identify Crime Patterns

Document Type

Abstract

Publication Date

Spring 5-1-2019

Abstract

Crime is prevalent everywhere. However, crime activity, such as the types of crimes commonly committed and the neighborhoods that are usually associated with crime, varies in every city. People’s motivation to commit a crime is often unknown. Therefore, it is difficult to identify steps to take to ensure safety at all times. CeaseCrime uses data from Kaggle to identify crime patterns within Vancouver and Boston. Factors such as weather, time of day, and neighborhood characteristics are analyzed to understand their correlation with crime. Using Machine Learning algorithms, multiple experiments are conducted to make predictions on which is the most dominant factor in crime activity and predictions on when and where a crime will likely happen in each city. Visualizations are created to demonstrate the results obtained. These visualizations and results are displayed on a website. There is a written report that documents all pre-processing decisions, predictions, and results.

Comments

Completed as part of the Computer Science Senior Capstone Project.

This document is currently not available here.

Share

COinS