| dc.description.abstract | In the rapidly growing media streaming platforms, it has become very challenging for users to browse through the catalogue and find interesting media items to watch. As such, personalized recommender systems are a vital component of this domain. Recommender systems are digital tools that have shown to be effective in supporting users in the discovery of items tailored to their personal preferences and needs.
Traditional recommender systems build profiles of users based on their static preferences (e.g., clicks or ratings) provided for items and utilize these profiles to generate relevant recommendations for users. However, these systems fail to consider that users' behaviors and preferences are not necessarily static properties - they change over time and depend on their contextual circumstances at the time of consumption. The most relevant items when the user was curled up on the couch watching TV in the evening might not be the most relevant items when they're on the school bus and watching from their phone.
In this thesis I address this problem by proposing a recommender system that utilizes contextual factors such as `Time of Day' and `Day of Week'. This methodology has been tested under two conditions: our offline evaluation setup, and online A/B testing on the largest Norwegian media streaming platform, TV 2 Play. The results show that the proposed recommender system is highly effective in generating recommendations for real users and, in the most of the cases, surpass today's industry-standard traditional recommender systems with respect to various metrics, including Precision, Recall, F1, MAP, and Coverage. | |
