The insurance claim is a basic problem in insurance companies. Insurance insurers always have a challenge to the growing of insurance claim loss. Because there is the occurrence of claim fraud and the volume of claim data increases in the insurance companies. Risks vary widely from one customer to another, and an accurate understanding of the different risk factors helps predict the probability of insurance claims based on historical data. In this study, is to build an accurate auto insurance claims prediction model through machine learning techniques. Focusing on advanced statistical methods and machine learning algorithms. The search was carried out using (Xgboost).Algorithm performance is evaluated using the mechanism, Precision, Recall, and F scale.