Zhiqi Zhang, Zhiyu Zeng, Ruohan Zhan, Dennis Zhang
arXiv 4 Feb 2026 · Econometrics
arXiv:2602.05099 · PDF · DOI · OpenAlex · Extracted main text
Randomized Controlled Trials (RCTs), or A/B testing, have become the gold standard for optimizing various operational policies on online platforms. However, 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.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Farrell, Max H and Liang, Tengyuan and Misra, Sanjog (2020) Deep learning for individual heterogeneity: an automatic inference framework | 1.000 | 13 | 3 | 100% |
| 2 | Athey, Susan and Wager, Stefan (2021) Policy learning with observational data | 0.811 | 4 | 2 | 100% |
| 3 | Zhou, Zhengyuan and Athey, Susan and Wager, Stefan (2023) Offline multi-action policy learning: Generalization and optimization | 0.811 | 4 | 2 | 100% |
| 4 | Chernozhukov, Victor and Demirer, Mert and Lewis, Greg and Syrgkanis… (2019) Semi-parametric efficient policy learning with continuous actions | 0.737 | 3 | 2 | 100% |
| 5 | Dubé, Jean-Pierre and Misra, Sanjog (2023) Personalized pricing and consumer welfare | 0.737 | 3 | 2 | 100% |
| 6 | Yoganarasimhan, Hema and Barzegary, Ebrahim and Pani, Abhishek (2023) Design and evaluation of optimal free trials | 0.737 | 3 | 2 | 100% |
| 7 | Farrell, Max H and Liang, Tengyuan and Misra, Sanjog (2021) Deep neural networks for estimation and inference | 0.644 | 2 | 2 | 100% |
| 8 | Kingma, Diederik P and Ba, Jimmy (2014) Adam: A method for stochastic optimization | 0.644 | 2 | 2 | 100% |
| 9 | Tian, Longxiu and Feinberg, Fred M (2020) Optimizing price menus for duration discounts: A subscription selectivity field experiment | 0.644 | 2 | 2 | 100% |
| 10 | Van der Vaart, Aad W (2000) Asymptotic statistics | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 78 scored citations.