Proactive In-Car Function Recommendations
Developed patent-pending ML classification model for proactive in-car function recommendations and published the research. Built pipelines processing terabytes of customer vehicle fleet data, created dataset of 716K function activations, and designed proxy labeling methodology to create experience labels from driving context to train predictive models.
Patent & Publication
Patent Application: WO2023156036A1 A computer-implemented method for providing a function recommendation in a vehicle, a vehicle and a system for implementing the method Published international patent application, now in national examination phase
Additional Related Research
Paper on integrating customer usage data in product development: Leveraging BMW fleet data for customer integration in product development
This paper explores the broader process of using fleet data to integrate customer insights into BMW's product development. Personalized proactive function recommendations are presented as an example application of customer usage data, enabling automotive manufacturers to recommend the right function at the right time for personalized customer experience.