296
Asian Journal of Engineering, Sciences and Technology - Volume 11, Issue 1 2021
By Noman Islam, Ammara Yaseen, Aqsa Ghaffar
Keywords: Context-aware recommendation, music recommendation, collaborative filtering.
Recommender systems are often seen as the key success factor for companies like Amazon, YouTube, Google, Netflix, and Spotify. It has become a major research topic with the goal of assisting users in finding items online by providing suggestions that closely match their preferences. Context-aware recommendation system employs the situation or the context to provide user preferences. In this paper, we consider two contextual situations drivers' current mood and driving style to recommend music while traveling. The proposition has been implemented based on collaborative filtering and evaluated using python library. In collaborative filtering, a rating matrix is maintained containing the ratings of the items provided by the user in past. This rating matrix can then be used to provide rating for the items that has not been rated by the user. While rating, the context of the user can also be considered. The performance of the proposed approach is determined based on various metrics such as mean absolute error (MAE), precision and recall.