International Research Journal of Education and Technology

Crime prediction plays an important role in maintaining public safety and improving law enforcement strategies. Traditional crime analysis methods are often manual and time-consuming, limiting their efficiency. Machine Learning (ML) techniques provide automated and data-driven approaches to forecast crime trends more accurately. This study reviews various ML models used in crime rate prediction, including supervised and unsupervised learning methods as well as deep learning approaches. It highlights the importance of spatial and temporal data, along with demographic and environmental factors, in improving prediction performance. The effectiveness of these models is measured using evaluation metrics such as accuracy, precision, recall, and F1-score. The paper also discusses existing challenges and explores future directions for enhancing ML-based crime prediction systems.

KEYWORDS

Crime Prediction, Machine Learning, Data Mining, Predictive Analytics, Spatial Analysis