Time-Dependent Clustering of TV Viewers
Web-based catch-up TV services allow users to watch programs at their favoured time and device and are revolutionizing the TV watching habits. With the increasing demand for catch-up TV, it has become evident that there is a need for personalised recommendations that will help users to pick programs from a large collection of available content. In order to mitigate the cold start problem, a catch-up TV recommender needs to exploit information pertaining to groups of users and their watching patterns. This paper presents an explorato-ry study into the watching patterns and stability of the identified user groups us-ing a new large-scale dataset gathered by a national Australian catch-up TV services provider. Using clustering, we were able to identify eight distinct and meaningful groups of users. We further analysed these groups and found that groups with highly dominant watching patterns stabilise and can be identified sooner and more accurately than the others. Our work provides the foundation for developing future catch-up TV recommender systems.