<![CDATA[This study originated from the increase in theft cases in the jurisdiction of Banjarbaru District Police which resulted in material and psychological losses for victims and disturbed the overall sense of security of the community. The research aims to develop a method that can assist the police in preventing and tackling theft crimes more effectively using machine learning algorithms. Research methods include research design, quantitative approach, and data collection and analysis techniques. The data analyzed included various categories of relevant information, such as the victim's gender, age, occupation, location of the incident, as well as details related to the modus operandi and losses suffered by the victim. The main data used is data on victims of theft crimes in the Banjarbaru Police jurisdiction during the 2019-2023 period. Data collection was carried out using primary data available from Min Ops Reskrim Polresta Banjarbaru. using the K-Nearest Neighbor (KNN) and Naïve Bayes (NB) algorithms to process historical data on theft crimes in Banjarbaru. The results reveal the general characteristics of theft cases, including time patterns, locations, and modus operandi, and compare the effectiveness between KNN and NB algorithms in predicting theft crimes. The conclusions emphasize the potential of machine learning in identifying theft patterns and provide recommendations for further development to support better decision-making and planning of crime prevention strategies]]>
Copyrights © 2024
