Truthful Auctions for Automated Bidding in Online Advertising

Authors: Yidan Xing, Zhilin Zhang, Zhenzhe Zheng, Chuan Yu, Jian Xu, Fan Wu, Guihai Chen

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments to evaluate the performances of the proposed auction mechanism under various auto-bidding settings. The evaluation results demonstrate that the designed truthful auction can generally achieve more than 90% performance (in terms of revenue and social welfare) of the optimal baselines without the consideration of truthfulness.
Researcher Affiliation Collaboration Yidan Xing1 , Zhilin Zhang2 , Zhenzhe Zheng1, , Chuan Yu2 , Jian Xu2 , Fan Wu1 and Guihai Chen1 1Department of Computer Science and Engineering, Shanghai Jiao Tong University 2Alibaba Group
Pseudocode Yes Algorithm 1: A Family of Simple Truthful Auctions
Open Source Code No The paper does not contain an explicit statement or link to the open-source code for the methodology it describes.
Open Datasets No In this section, we conduct experiments with synthetic data to validate the performance of our proposed auctions. (...) Symmetric bidders Bidders are symmetric with vi,j U[1, 4], Bi U[40, 80] and Ri U[1, 3], where U[a, b] is the uniform distribution within the range [a, b].
Dataset Splits No The paper uses synthetic data generated based on specified distributions for its experiments and does not describe fixed training, validation, and test dataset splits from a pre-existing dataset. Results are averaged over multiple runs with newly generated data.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., Python, PyTorch, or specific solvers).
Experiment Setup Yes Rank Score Function We adopt rank scores in the form fi,j(R) = αi,j e βR, where αi,j is drawn from a rectified normal distribution N(µi, σ2 i ), and β, µi, σi are pre-set parameters. (...) Figure 3d reports a set of revenue and fairness performances with different β in the same setting as 400 items in Figure 3c.