Abstract

This dissertation investigates the methodological foundations and empirical applications of data-driven decision-making within digital platforms. By integrating causal inference, deep learning, and structural modeling, the following chapters develop rigorous frameworks to optimize platform interventions while providing formal theoretical guarantees for policy performance and how recommendation systems influence user behavior, creating broader impacts on content consumption and production beyond immediate engagement metrics. In Chapter 1, “Personalized Policy Learning through Discrete Experimentation: Theory and Empirical Evidence,” we note that randomized control trials (RCTs) on these platforms typically cover a limited number of discrete treatment levels, while the platforms increasingly face complex operational challenges involving optimizing continuous variables, such as pricing and incentive programs. The current industry practice involves discretizing these continuous decision variables into several treatment levels and selecting the optimal discrete treatment level. This approach, however, often leads to suboptimal decisions as it cannot accurately extrapolate performance for untested treatment levels and fails to account for heterogeneity in treatment effects across user characteristics. This study addresses these limitations by developing a theoretically solid and empirically verified framework to learn personalized continuous policies based on high-dimensional user characteristics, using observations from an RCT with only a discrete set of treatment levels. Specifically, we introduce a deep learning for policy targeting (DLPT) framework that includes both personalized policy value estimation and personalized policy learning. We prove that our policy value estimators are asymptotically unbiased and consistent, and the learned policy achieves a root-n-regret bound. We empirically validate our methods in collaboration with a leading social media platform to optimize incentive levels for content creation. Results demonstrate that our DLPT framework significantly outperforms existing benchmarks, achieving substantial improvements in both evaluating the value of policies for each user group and identifying the optimal personalized policy. In Chapter 2, “The Impact of Recommender Systems on Content Consumption and Production: Evidence from Field Experiments and Structural Modeling,” we observe that online content-sharing platforms such as TikTok and Facebook have become integral to daily life, leveraging complex algorithms to recommend user-generated content (UGC) to other users. While prior research and industry efforts have primarily focused on designing recommender systems to enhance users' content consumption, the impact of recommender systems on content production remains understudied. To address this gap, we conducted a randomized field experiment on one of the world's largest video-sharing platforms. We manipulated the algorithm's recommendation of creators based on their popularity, excluding a subset of highly popular creators' content from being recommended to the treatment group. Our experimental results indicate that recommending content from less popular creators led to a significant 1.34\% decrease in video-watching time but a significant 2.71\% increase in the number of videos uploaded by treated users. This highlights a critical trade-off in designing recommender systems: popular creator recommendations boost consumption but reduce production. To optimize recommendations, we developed a structural model wherein users' choices between content consumption and production are inversely affected by recommended creators' popularity. Counterfactual analyses based on our structural estimation reveal that the optimal strategy often involves recommending less popular content to enhance production, challenging current industry practices. Thus, a balanced approach in designing recommender systems is essential to simultaneously foster content consumption and production.

Committee Chair

Dennis Zhang

Committee Members

Fuqiang Zhang; Lingxiu Dong; Ruohan Zhan; Tat Chan; Xiang Hui

Degree

Doctor of Philosophy (PhD)

Author's Department

Supply Chain, Operations, and Technology

Author's School

Olin Business School

Document Type

Dissertation

Date of Award

5-5-2026

Language

English (en)

Download

Share

COinS