A Game-theoretic Machine Learning Approach for Revenue Maximization in Sponsored Search

TL;DR

This paper introduces a game-theoretic machine learning framework that optimizes auction mechanisms for sponsored search revenue by modeling advertiser bid dynamics and applying bilevel optimization with genetic algorithms.

Contribution

It proposes a novel bilevel optimization approach combining machine learning and game theory to learn auction mechanisms from historical data.

Findings

The approach converges to optimal revenue as prediction period increases.

Genetic programming effectively optimizes the auction mechanism.

The method outperforms several baseline auction strategies.

Abstract

Sponsored search is an important monetization channel for search engines, in which an auction mechanism is used to select the ads shown to users and determine the prices charged from advertisers. There have been several pieces of work in the literature that investigate how to design an auction mechanism in order to optimize the revenue of the search engine. However, due to some unrealistic assumptions used, the practical values of these studies are not very clear. In this paper, we propose a novel \emph{game-theoretic machine learning} approach, which naturally combines machine learning and game theory, and learns the auction mechanism using a bilevel optimization framework. In particular, we first learn a Markov model from historical data to describe how advertisers change their bids in response to an auction mechanism, and then for any given auction mechanism, we use the learnt model to predict its corresponding future bid sequences. Next we learn the auction mechanism through empirical revenue maximization on the predicted bid sequences. We show that the empirical revenue will converge when the prediction period approaches infinity, and a Genetic Programming algorithm can effectively optimize this empirical revenue. Our experiments indicate that the proposed approach is able to produce a much more effective auction mechanism than several baselines.