We study the problem of route recommendation to idle taxi drivers such that the distance between the taxi and an anticipated customer request is minimized. Minimizing the distance to the next anticipated customer leads to more productivity for the taxi driver and less waiting time for the customer. To anticipate when and where future customer requests are likely to come from and accordingly recom- mend routes, we develop a route recommendation engine called MDM: Minimizing Distance through Monte Carlo Tree Search. In contrast to existing techniques, MDM employs a continuous learning platform where the underlying model to predict future customer requests is dynamically updated. Extensive experiments on real taxi data from New York and San Francisco reveal that MDM is up to 70% better than the state of the art and robust to anomalous events such as concerts, sporting events, etc.