Online Ad Allocation with Predictions

TL;DR

This paper introduces a machine learning-augmented online ad allocation algorithm that leverages predictions to improve performance over traditional worst-case algorithms, demonstrating robustness and effectiveness on real-world data.

Contribution

It develops a novel prediction-based algorithm for online ad allocation that outperforms worst-case algorithms and is robust to prediction inaccuracies.

Findings

Outperforms traditional algorithms on synthetic data

Effective on real-world ad allocation datasets

Robust to inaccurate predictions

Abstract

Display Ads and the generalized assignment problem are two well-studied online packing problems with important applications in ad allocation and other areas. In both problems, ad impressions arrive online and have to be allocated immediately to budget-constrained advertisers. Worst-case algorithms that achieve the ideal competitive ratio are known, but might act overly conservative given the predictable and usually tame nature of real-world input. Given this discrepancy, we develop an algorithm for both problems that incorporate machine-learned predictions and can thus improve the performance beyond the worst-case. Our algorithm is based on the work of Feldman et al. (2009) and similar in nature to Mahdian et al. (2007) who were the first to develop a learning-augmented algorithm for the related, but more structured Ad Words problem. We use a novel analysis to show that our algorithm is able to capitalize on a good prediction, while being robust against poor predictions. We experimentally evaluate our algorithm on synthetic and real-world data on a wide range of predictions. Our algorithm is consistently outperforming the worst-case algorithm without predictions.