Publication Type

Conference Paper

Version

submittedVersion

Publication Date

1-2014

Abstract

Internet TV has attracted a significant amount of attention from the conventional cable TV service providers, by providing customized TV programs at preferred time slots. The cable TV service providers are seeking to retain their customers by giving them a better experience: by understanding their customers’ preferences and upselling them the right products to cater to their interests. It is not easy to understand customer preferences though, since customers are not able to watch channels to which they have not subscribed. This makes it difficult to predict what they will like to watch, as a result. In this paper, I discuss my ongoing research on TV viewership behavior. I model customer preferences using a technique called latent Dirichlet analysis (LDA), by considering channel viewing behavior as a similar process of article generation. Customer preferences over unsubscribed channel are calculated from the LDA model. My model achieves better prediction performance as a result. I also present a quantitative case study to show that the observed channel viewing behavior makes sense.

Keywords

Cable TV, customer targeting, data mining, retail telecom services, viewership pattern

Discipline

Computer Sciences | Recreation Business

Publication

Pacific Telecommunications Council (PTC’14)

Publisher

IEEE

City or Country

Honolulu, Hawaii

Copyright Owner and License

LARC

Share

COinS