DATA ANALYTICS MODELS FOR CRIME PREDICTION: A SUMMARY STUDY

Abstract

Machine-learning and deep-learning models are powerful tools for crime prediction. Using historical data, these models can identify patterns and trends, as well as estimate the likelihood of crime occurring in specific locations. Autonomous learning models include logistic regression, vector support machines (SVM), and decision trees, which are relatively simple and interpretable, but may have limitations with complex, nonlinear data. On the other hand, deep learning models, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversaries (GANs), can handle more complex data and capture intricate patterns, but they require large amounts of data and can be difficult to interpret. The choice of the right model will depend on the characteristics of the problem and the available data, taking advantage of the strengths of each approach.