<![CDATA[The high crime rate in Riau Province poses a serious threat to social stability and public safety, requiring accurate prediction strategies to support crime prevention efforts. Based on data from the Central Statistics Agency (BPS), Riau ranked seventh among the provinces with the highest crime rates in Indonesia in 2022, indicating that conventional prevention efforts remain insufficient. However, studies applying statistical data-based prediction models to crime in Riau are still limited, creating a gap in data-driven decision making. This study aims to develop a crime rate prediction model in Riau Province using the Multiple Linear Regression (MLR) method with BPS crime data from 2019–2023. The independent variables include six types of crime: corruption, drug dealers, drug users, terrorism, illegal logging, and human trafficking, while the dependent variable is the total number of crimes per district or city. The research process involved data collection, understanding, preprocessing, application of linear regression algorithms, model training and testing, and evaluation using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The results show that Pekanbaru City recorded the highest number of cases, mostly related to drug crimes. The model predicts an increase in Pekanbaru’s cases from 3,331 in 2024 to 5,852 in 2027, while Dumai City is projected to decline from 543 to 397 cases. The model demonstrates high accuracy in most areas, particularly in Kampar (MAPE 0.28%), Siak (0.52%), and Rokan Hilir (0.94%), though less accurate in the Meranti Islands (565.99%) due to data instability. These findings prove that the Multiple Linear Regression method effectively predicts crime trends and can serve as a quantitative decision-making tool for law enforcement and local governments. Further research should include socioeconomic factors such as poverty and unemployment, and compare results with alternative forecasting methods like ARIMA and Exponential Smoothing to enhance prediction accuracy.]]>
