Crime Data Mining for D.C. area

TR Number
Date
2020-05-04
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract

With millions of crime offenses are recorded each year in the United States, regardless of our position or background in the community, safety and security are our top concern when we are in an area. To help increase the community's confidence in public safety, our team proposed a product that can help people view the crime history as well as predict future times and places for crimes in the Washington D.C. area. This product is designed for a typical worker, a real estate agent, a regular student, a researcher or an analyst that are interested in exploring the likelihood of crime to occur in the area to ensure safety. The product provides users with analysis on the count of records in yearly cases or in each ward in the metropolitan area, analysis on how different machine learning models can effectively classify and predict the offense group. Our product also provides time series analysis in each census tract and thus, can predict the crime trend in the same census tract in the upcoming month.

Description
Keywords
crime data mining, crime data, machine learning, time series analysis, public safety, Washington D.C.
Citation