Sequential Selection of Correlated Ads by POMDPs

TL;DR

This paper introduces a POMDP-based approach for online ad selection that leverages ad correlations to optimize long-term revenue, balancing exploration and exploitation effectively.

Contribution

It presents a novel POMDP model utilizing ad correlations for improved ad selection, with a belief update method similar to collaborative filtering, enhancing exploration efficiency.

Findings

Our algorithms outperform strong baselines in real-world datasets.

Leveraging ad correlations improves long-term ad revenue.

The model effectively balances exploration and exploitation.

Abstract

Online advertising has become a key source of revenue for both web search engines and online publishers. For them, the ability of allocating right ads to right webpages is critical because any mismatched ads would not only harm web users' satisfactions but also lower the ad income. In this paper, we study how online publishers could optimally select ads to maximize their ad incomes over time. The conventional offline, content-based matching between webpages and ads is a fine start but cannot solve the problem completely because good matching does not necessarily lead to good payoff. Moreover, with the limited display impressions, we need to balance the need of selecting ads to learn true ad payoffs (exploration) with that of allocating ads to generate high immediate payoffs based on the current belief (exploitation). In this paper, we address the problem by employing Partially observable Markov decision processes (POMDPs) and discuss how to utilize the correlation of ads to improve the efficiency of the exploration and increase ad incomes in a long run. Our mathematical derivation shows that the belief states of correlated ads can be naturally updated using a formula similar to collaborative filtering. To test our model, a real world ad dataset from a major search engine is collected and categorized. Experimenting over the data, we provide an analyse of the effect of the underlying parameters, and demonstrate that our algorithms significantly outperform other strong baselines.