RESEARCH PROJECTS
with Puneet Manchanda and Eric Schwartz
Free ad-supported streaming of on-demand content is growing. Platforms that provide this service need to find a balance between the interest of the viewer (to increase content consumption) with the incentives of the platform (to decrease ad avoidance). Using causal machine learning methods that combine debiased machine learning with instrumental variables, we capture the causal effect of four independent levers of ad delivery on content consumption and ad avoidance. We investigate whether there exists a sweet spot in the values of these levers that balance the interest of both stakeholders. Our results show that a decrease in the number of pods (ad breaks) or length of pods results in an increase in content consumption and a decrease in ad avoidance. Similarly, an increase in the diversity of ads decreases ad avoidance but has no material impact on content consumption. However, we observe a tradeoff for spacing till the next pod. An increase in spacing results in an increase in content consumption but at the cost of an increase in ad avoidance. We discuss the theoretical mechanisms behind our findings and present implications of our results for streaming platforms.
Keywords: Streaming Platforms, Ad Avoidance, Ad Levers, Causal Inference, Debiased Machine Learning
INFLUENCER VIDEOS: UNBOXING THE MYSTIQUE
with Puneet Manchanda
Influencer marketing has become a very popular tool to reach customers. Despite the rapid growth in influencer videos, there has been little research on the effectiveness of their constituent features in explaining video engagement. We study YouTube influencers and analyze their unstructured video data across text, audio and images using an “interpretable deep learning” framework that accomplishes both goals of prediction and interpretation. Our prediction-based approach analyzes unstructured data and finds that “what is said” in words (text) is more influential than “how it is said” in imagery (images) or acoustics (audio). Our novel interpretation-based approach is implemented after completion of model prediction by analyzing the same source of unstructured data to measure importance attributed to the video features. We eliminate several spurious relationships in two steps, identifying a subset of relationships which are confirmed using theory. We uncover novel findings that establish distinct associations for measures of shallow and deep engagement based on the dual-system framework of human thinking. Our approach is validated using simulated data, and we discuss the learnings from our findings for influencers and brands.
Keywords: Influencer Marketing, Video Advertising, Social Media, Interpretable Deep Learning, Transfer Learning