In the insurance broker market, commissions received by brokers are closely related to so-called "customer value": the longer a policyholder keeps their contract, the more profit there is for the company and therefore the broker. Hence, predicting the time at which a potential policyholder will surrender their contract is essential in order to optimize a commercial process and define a prospect scoring. In this paper, we propose a weighted random forest model to address this problem. Our model is designed to compensate for the impact of random censoring. We investigate different types of assumptions on the censor-ing, studying both the cases where it is independent or not from the covariates. We compare our approach with other standard methods which apply in our setting, using simulated and real data analysis. We show that our approach is very competitive in terms of quadratic error in addressing the given problem.