BAT: Benchmark for Auto-bidding Task

Abstract

The optimization of bidding strategies for online advertising slot auctions presents a critical challenge across numerous digital marketplaces. A significant obstacle to the development, evaluation, and refinement of real-time autobidding algorithms is the scarcity of comprehensive datasets and standardized benchmarks. To address this deficiency, we present an auction benchmark encompassing the two most prevalent auction formats. We implement a series of robust baselines on a novel dataset, addressing the most salient Real-Time Bidding (RTB) problem domains: budget pacing uniformity and Cost Per Click (CPC) constraint optimization. This benchmark provides a user-friendly and intuitive framework for researchers and practitioners to develop and refine innovative autobidding algorithms, thereby facilitating advancements in the field of programmatic advertising. The implementation and additional resources can be accessed at the following repository (https://github.com/avito-tech/bat-autobidding-benchmark, https://doi.org/10.5281/zenodo.14794182).

11 pages, 10 figures, WWW 2025 conference

References in corpus (9)

• Real-Time Bidding by Reinforcement Learning in Display Advertising
• Bid Optimization by Multivariable Control in Display Advertising
• Learning optimization models in the presence of unknown relations
• Sequential Selection of Correlated Ads by POMDPs
• Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising
• Users and Contemporary SERPs: A (Re-)Investigation Examining User Interactions and Experiences
• Bid Shading by Win-Rate Estimation and Surplus Maximization
• Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions
• Optimization of a SSP's Header Bidding Strategy using Thompson Sampling