Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning

TL;DR

This paper introduces a novel game-theoretic offline reinforcement learning approach for marketing budget allocation, demonstrating its effectiveness and convergence guarantees in large-scale real-world campaigns.

Contribution

It proposes a new offline value-based reinforcement learning method with mixed policies that is practical, converges to the optimal policy, and outperforms baselines in large-scale marketing campaigns.

Findings

Method outperforms baseline methods in large-scale experiments.

Guarantees convergence to the optimal policy.

Successfully deployed in a real marketing campaign with millions of users.

Abstract

We study the budget allocation problem in online marketing campaigns that utilize previously collected offline data. We first discuss the long-term effect of optimizing marketing budget allocation decisions in the offline setting. To overcome the challenge, we propose a novel game-theoretic offline value-based reinforcement learning method using mixed policies. The proposed method reduces the need to store infinitely many policies in previous methods to only constantly many policies, which achieves nearly optimal policy efficiency, making it practical and favorable for industrial usage. We further show that this method is guaranteed to converge to the optimal policy, which cannot be achieved by previous value-based reinforcement learning methods for marketing budget allocation. Our experiments on a large-scale marketing campaign with tens-of-millions users and more than one billion budget verify the theoretical results and show that the proposed method outperforms various baseline methods. The proposed method has been successfully deployed to serve all the traffic of this marketing campaign.