Can I See Beyond What You See? Blending Machine Learning and Econometrics to Discover Household TV Viewing Preferences

This research blends machine learning-based discovery of preference patterns that uses natural language processing for TV viewing data with explanatory modeling that uses econometrics, as a basis for understanding TV viewing preferences at the household-level. We employ a dataset of about 1.1 million observations that was collected via set-top box technology that tracked household-level consumption of the content of its channel subscription package. The data describe the details of what households watched on TV, including the channels and shows, start times and durations, and overall viewing times for content from different digital entertainment genres. This research demonstrates the efficacy of our machine learning and explanatory econometrics approach, and presents insights on consumer behavior and content bundling that are useful for firm strategy in digital entertainment services.