The comparative analysis on the accuracy of k-NN, Naive Bayes, and Decision Tree Algorithms in predicting crimes and criminal actions in Sleman Regency

Abstract

Crime is an action which is considered as a violation of law and can harm others. Nowadays, crimes has increased with erratic patterns. Therefore, crime prevention is necessary since it will occur based on the historical data. Data mining is a technique that can be used to predict crimes that will occur. According to the previous researches, data mining techniques have several methods that can be used to predict crimes by utilizing the data of crimes that have occurred. Hence, it is necessary to conduct a comparative analysis of classification algorithms in order to obtain accurate prediction results based on the crime data in Sleman regency. The classification algorithms analyzed in this study were k-NN, Naive Bayes, and Decision Tree. Based on the three algorithms, the accuracy of k-NN with k = 5 was 57.88 percent, with k = 10 was 59.49 percent, with k = 15 is 59.38 percent, with k = 20 was 60.18 percent, and with k = 25 was 61.57 percent. Meanwhile, for the Naive Bayes algorithm, the accuracy reached 65.59 percent, and the Decision Tree algorithm reached 60.23 percent. In conclusion, the algorithm with the highest accuracy was owned by Naive Bayes.

Crime forecasting: a machine learning and computer vision approach to crime prediction and prevention

“…Third, in refs. [ 60 , 61 ], a novel crime detection technique called naïve Bayes was implemented for crime prediction and analysis. Jangra and Kalsi [ 60 ] achieved an astounding crime prediction accuracy of 87%, but could not apply their approach to datasets with a large number of features.…”

“…Jangra and Kalsi [ 60 ] achieved an astounding crime prediction accuracy of 87%, but could not apply their approach to datasets with a large number of features. By contrast, Wibowo and Oesman [ 61 ] achieved an accuracy of only 66% in predicting crimes and failed to consider the computational speed, robustness, and scalability.…”

“… This paper presented comparative analysis on the accuracy of k-NN, naive Bayescand decision tree algorithms in predicting crimes and criminal actions. [ 61 ] 7 Autoregressive integrated moving average (ARIMA) The mean absolute error and standard deviation of the model are (1) Test average test standard deviation is 0.0867 ± 0.0293; (2) Training average training standard deviation is 0.0413 ± 0.0084. They have described this model as quite complex compared to others.…”

Comparative Analysis Among Decision Tree vs. Naive Bayes for Prediction of Weather Prognostication

“…Here, the internal nodes represent test on the attributes. For example, if u call the customer care it will redirect to Intelligent Computer Assistant and it will reply like press 1 for English and press 2 for Tamil, press 3 for Hindi and eventually it will redirect to the authorized person here the corporate using decision tree algorithm to require certain decisions [6]. The basic terminologies are given below: Root node: This can be a whole population or just a few.…”

Techniques for Predicting Dark Web Events Focused on the Delivery of Illicit Products and Ordered Crime

“…In a related study, Mahanolobis was described as a cybercrime analysing and prediction tool with a dynamic time wrapping approach that allows both the prediction of crime and the arrest of the actual perpetrator [11]. LE [12] in the USA, UK, and some European countries are currently using crime predicting applications to track criminal's activities on social platforms and zones. The mapping of ML approaches with technological automated systems and criminal intelligence has become a favorite tool for government agencies and the government.…”