A system and method for in-vehicle content recommendation is disclosed. The system comprises an aggregator module, a modeler module and a recommendation module. The aggregator module aggregates content data describing content such as a music, a news program, a podcast, an audio book, a movie, a television program, etc. The aggregator module also aggregates situation data describing an environment in which the content was recommended to a user, and feedback data describing the user's response to the recommendation. The modeler module generates a content preference model. The content preference model represents the user's dynamic content preferences based at least in part on the aggregated data. The recommendation module generates a first content recommendation based at least in part on the content preference model.