Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk
Authors: David Simchi-Levi, Chonghuan Wang
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we reveal the relationship among such three objectives. Under a linear structural model, we investigate the trade-offs between causal inference and expected revenue maximization, as well as between expected revenue maximization and tail risk control. Furthermore, we propose an optimal pricing experimental design, which can flexibly adapt to different desired levels of trade-offs. The provided paper focuses on theoretical analysis, lower bounds, optimal design (RSD algorithm), and relationships between objectives. |
| Researcher Affiliation | Academia | 1Laboratory for Information & Decision Systems, MIT 2Institute for Data, Systems, and Society, MIT 3Operations Research Center, MIT 4Department of Civil and Environmental Engineering, MIT 5Center for Computational Science and Engineering, MIT. |
| Pseudocode | Yes | Algorithm 1 Random Shock Design (RSD) |
| Open Source Code | No | The paper only provides a link to SSRN for the full version: “Finally, we remark that the full version of this paper (containing additional theoretical results, computational experiments, and missing proofs) is available at https: //ssrn.com/abstract=4357543.” This is not a link to source code. |
| Open Datasets | No | The paper formulates a “linear structural function” in Section 2, which describes the demand model Dt(p) = bp + θ xt + εt. This is a theoretical model for simulation, and the paper does not mention or link to any public or open datasets used for training. |
| Dataset Splits | No | The paper is theoretical and does not describe any specific dataset splits (training, validation, or testing) or cross-validation setups. It primarily focuses on theoretical derivations and algorithm design. |
| Hardware Specification | No | The paper does not specify any hardware details such as GPU models, CPU types, or cloud resources used for running experiments. It focuses on theoretical modeling and algorithm design. |
| Software Dependencies | No | The paper does not mention any specific software dependencies with version numbers (e.g., programming languages, libraries, frameworks, or solvers). It primarily presents theoretical results and an algorithm. |
| Experiment Setup | No | The paper does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size, epochs), model initialization, or specific training schedules. It introduces a parameter α within its theoretical framework but does not detail an empirical experimental setup. |