Finding the Sweet Spot: Ad Targeting on Streaming Media

Abstract

A majority of US households view on-demand content on streaming video services and ad spending on these online platforms is growing rapidly. However, extant research on streaming media has not explored the balance between the interest of the viewer (content consumption) with the incentives of the platform (ad exposure). We characterize this interplay using two new metrics based on viewing data on a streaming media platform. The first metric, Bingeability, measures non-linear content consumption while the second metric, Ad Tolerance, measures the willingness of a viewer to view ads and to continue viewing after ad exposure. Using causal machine learning methods that combine a tree-based model with instrumental variables, we capture the impact of ad delivery on Bingeability and Ad Tolerance for individual viewers for each viewing session. The results indicate that the average “sweet spot” that balances the interest of the viewer and the platform consists of short ad breaks that are equally spaced at long intervals during a viewing session. We discuss the implications of our results for managers of streaming platforms.

Keywords: Advertising, Targeting, Streaming Media, Machine Learning, Causal Inference

JEL Classification: M31, M37, C14, C36, C61