Automobile fraudulent claim leads to several consequences for the company and policyholder. The current detection system is costly and inefficient. This research aims to design a prediction model in detecting automobile insurance fraud using a machine learning approach. The study used realworld data on an automobile insurance company in Indonesia. The dataset has a high imbalanced distribution between the data of policyholders who commit fraud and legitimate data. This research handles the imbalanced dataset problem by using the Synthetic Minority Oversampling Technique (SMOTE) and undersampling methods. The proposed supervised classifiers are Multilayer Perceptron (MLP), Decision Tree C4.5, and Random Forest(RF). The performance of models is evaluated through the confusion matrix, ROC Curve, and parameters such as sensitivity. This research found that Random Forest outperformed the results comparing to other classifiers with 98.5% accuracy.