Personalized pricing is on the rise in the retail industry,and it's been used in many service platforms.Personalized pricing assumes that the platform has an idea of who the customer is,and allows the platform to incentivize the customers based on their characteristics and actions.In this work,we consider a personalized pricing problem with revisiting customers.We assume a customer's utility depends on some feature irfformation and some unobserved personal shock.For the case where customer utilities are unknown,we propose a heuristic that combines the idea of binary search and feature-based pricing,and show that it outperforms common benchmarks.We also demonstrate that if we have some information about either the customer utility or the dependence on the feature information,then we can learn the other much faster,and this is what we mean by the synergy between customer segmentation and personalization.This observation can help managers make better personalized decisions for customers that repeatedly interact with the platform.