Fire ignition is one of the events that can cause severe humanitarian, economic, and environmental damages. Fast fire detection can significantly help in controlling the fire and reducing the resulting losses. Efficient fire-fighting in schools can save many lives and resources. In this study, a data mining-based fire detection system is proposed. It can be used in detecting fire sources in different locations of Kuwaiti schools that are listed in the ministry of Education. The proposed system consists of four main steps: data acquisition, data preprocessing, feature analysis and selection, and classification. The data acquisition is performed with the help of the General Civil Defense Department of Kuwait. In the data preprocessing step, a set of operations is performed on the collected data, including discretization and categorization. In the feature selection step, two feature selection techniques are used, namely Information Gain (IG) and Principle Component Analysis (PCA). Finally, in the classification step, five classification models are used to perform the classification task, including Decision Tree (DT), Linear Regression (LR), Linear Discriminant (LD), Support Vector Machine (SVM), and Deep Belief Network (DBN). Intensive experiments are performed to evaluate the proposed system, and the obtained results are auspicious.