Implementation of Predictive Crime Analytics in Municipal Crime Management System in Calauan, Laguna, Philippines

Abstract

© 2020, World Academy of Research in Science and Engineering. All rights reserved. Predictive crime analytics is a process of evaluating a dataset to discover veiled patterns that can be useful in forecasting crime occurrence. The application of a machine learning algorithm is widely used in developing artificial intelligence to integrate into computer systems. This project aims to develop a management system for crime records implementing predictive crime analytics in forecasting crime occurrences. Through predictive crime analytics and software development life cycle, a management information system that is capable of forecasting crime was successfully developed. A predictive model was designed using multinomial logistic regression, which acquires a totality accuracy of 86.60% and prediction confidence. It is also shown in this paper that regression is better than other classification algorithms in terms of predicting crime occurrence. Moreover, discussed in this research, among all the barangay in Calauan, Laguna. Dayap is the most vulnerable in different index crimes like rape, murder, robbery, theft, homicide, and illegal drugs.