Multi-Context Recommendation Systems (CARS) in Autonomous Driving and Other Applications

Recommendation systems (RS) are important for their instantaneous ability to suggest to users their desired items and for ensuring a smooth and worthwhile user experience. To optimize the user's experience with the RS, it can be programmed to be aware of the various contexts the user has while interacting with the system. Context-aware recommendation systems (CARS) aim to add more nuance to the process of predicting items by considering different factors such as location and time. This paper presents the foundations of recommendation systems, such as categories, evaluation metrics, datasets, and challenges. In this paper, we show the effectiveness of multi-contexts in autonomous driving. Three CARS models are developed and tested. Experimental results show that adding multi-contexts provides more personalized options for drivers, allowing intelligent decisions.