ANALYSING SPATIAL-TEMPORAL DISTRIBUTION OF CRIME HOTSPOTS AND THEIR RELATED FACTORS USING DECISION TREE TECHNIQUE

Abstract

There had been a colossal upturn in the criminality in the recent past. Law violations are a common social issue affecting the quality of life and the economic growth of a city/country. A crime incident is a multi-dimensional complex phenomenon that is closely associated with temporal, spatial, societal, and ecological factors. Data mining is a way to extract knowledge out of usually large data sets; in other words, it is an approach to discover hidden relationships among data by using artificial intelligence methods of which decision tree is inclusive. The wide range of machine learning applications has made it an important field ofresearch. Criminology is one ofthe most important fields for applying data mining. With the rise of crimes, security forces continuing to demand advanced systems and new approaches to improve crime analytics and better protect their communities. Crime forecasting is notoriously difficult. In an attempt to utilize all these factors in crime pattern formulation, we propose a new feature construction and feature selection framework for crime forecasting. A new concept of multi-dimensional feature denoted as spatio-temporal pattern, is constructed from local crime cluster distributions in different time periods at different granularity levels. We applied Decision tree applied in the context oflaw enforcement and intelligence analysis holds the promise of alleviating such problem. This study considered the development of crime prediction prototype model using decision tree algorithm. Decision Tree Algorithm and Google Map API are used for the analysis ofthe dataset. We used dataset for real-world crimes in a city ofthe US, Fort Worth. After gathering the data, we had built the desired model for the analysis of the required model on dataset.