Personalized TV program guide based on neural network

As digital TV providers today offer hundreds of channels, TV viewers do not have problem with content availability, but with finding an interesting content in a reasonable time instead. In a situation like this, both the providers and the viewers would benefit from personalized TV program guides, the tools that would track and learn the viewers' preferences and then recommend them the content they would like. In this paper, we propose one such guide which is based on artificial neural network. We examine and compare several learning algorithms, with recommendation accuracy and neural network training time as performance metrics.