In this thesis we present the development of an individual preference recognition system. We demonstrate the utilization of past route choices to personalize navigation experiences, as most automotive systems require a manual setting of routing preferences. We begin with a comprehensive overview of current routing technologies and existing methods for user preference recognition. After defining a set of requirements, we select the most suitable technologies. Then, we determine custom preferences and data sources, and describe how to incorporate them into the preference recognition algorithm. With these findings, we implement a prototype of the customized algorithm. We discuss the development of the single components e.g. preference data structure, routing interface and the learning algorithm. In the evaluation process of this prototype, we include experimental setups that assess the system’s effectiveness in a virtual scenario, showcasing its capability to understand individual and represent user behavior. By demonstrating the enhancement of preference analyses with an arbitrary number of factors, we contribute to the advancement of more personalized and intuitive navigation systems. We can conclude from the evaluation, that our predictions are in fact accurate, enabling us to integrate this method with route provider interfaces. This will allow us to examine real user data in the future.