Intelligent Investigation on Crime Incident Reports in the Province of Laguna through Predictive Model Development

Abstract

© 2020, World Academy of Research in Science and Engineering. All rights reserved. In the past years, crime becomes one of the main concerns in the Philippines for it affects drastically in the economic growth of the country. Awareness was one of the key factors that a police officer must possessed to effectively reduced crime in particular location. Many criminologists study on the number or occurrence of a crime to resolve the problem, however, number vagueness and possible source are often encountered that compromises the possible real effects or pattern. Machine learning is well-known to produce new knowledge and discover hidden pattern intelligently in particular database which can be used to produce data-driven reasoning or policy recommendation. The key objective of this research is to develop a predictive model in investigating crime records in the province of Laguna. Following the famous concept of knowledge discovery in databases, the researchers found out that decision tree algorithm is the best machine learning algorithm in classifying crime occurrence. Furthermore, date, time and place have a significant correlation in crime occurrence. Also shown in this paper, that the bigger district in the province of Laguna is more vulnerable in different crime.