PhD Candidate - Quantitative Marketing
Ross School of Business
University of Michigan
2015 - 2021 (Expected)

My research interests lie in understanding and documenting the experiential consumption of digital products and media. I do this by implementing causal and/or interpretable machine learning methods on behavioral data. These interests are reflected in my dissertation titled “Modelling viewer and influencer behavior on streaming platforms,” that comprises of two essays. In the first essay, “Finding the Sweet Spot: Ad Scheduling on Streaming Media”, which has been invited for revision at the Journal of Marketing Research, I design an ‘optimal’ ad schedule that balances the interest of the viewer (watching content) with that of the streaming platform (ad exposure). This is accomplished with the help of causal and interpretable tree-based learning methods applied on a dataset of Hulu customers. In my second essay, “Video Influencers: Unboxing the Mystique”, which is also my Job Market Paper, I study the relationship between advertising content in YouTube influencer videos (across text, audio and images) and marketing outcomes, and also investigate whether influencers “learn” these relationships over time. This is accomplished with the help of novel interpretable deep-learning approaches that avoid making a trade-off between predictive ability and interpretability. My approach not only predicts well out-of-sample but also allows for interpretation of the attention paid on video elements.

© June 2020 by Prashant Rajaram