Crime is considered a major issue that affects society, with incidents occurring frequently and in large numbers. Information on crime rates over time, including the date and number of crimes recorded each year, is provided in this dataset. In this project, the crime rate is analyzed. The crime rate (dependent variable) will be predicted according to the year, location, and crime type (independent variables) using Random Forest which is a type of machine learning (ML) algorithm. In machine learning, the Random Forest algorithm is a robust ensemble learning method. It functions by creating multiple decision trees during the training phase, where each tree generates predictions. The final output is determined through averaging results (for regression) or voting by the majority (for classification), enhancing accuracy and reducing the risk of overfitting. The system will examine how the crime information can be converted into a regression problem, thus assisting officials in solving crimes more efficiently. The societal and operational implications of these findings are emphasized, indicating how law enforcement agencies can efficiently distribute resources and mitigate crimes. Crime analysis is performed using available information to uncover crime trends. On the basis of territorial distribution of available data and the recognition of crimes, various multilinear regression techniques can be applied to predict crime frequency.