BAT: Benchmark for Auto-bidding Task

TL;DR

This paper introduces BAT, a comprehensive benchmark dataset and framework for developing and evaluating auto-bidding algorithms in online advertising, addressing the lack of standardized benchmarks and datasets in the field.

Contribution

It provides a novel dataset and benchmark for auto-bidding in two auction formats, enabling improved development and comparison of autobidding algorithms.

Findings

Implemented robust baselines on the dataset

Addressed budget pacing and CPC optimization

Facilitated research in autobidding algorithms

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).