Skip to yearly menu bar Skip to main content


Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising

Xiaotian Hao · Zhaoqing Peng · Yi Ma · Guan Wang · Junqi Jin · Jianye Hao · Shan Chen · Rongquan Bai · Mingzhou Xie · Miao Xu · Zhenzhe Zheng · Chuan Yu · HAN LI · Jian Xu · Kun Gai

Keywords: [ Combinatorial Optimization ] [ Deep Reinforcement Learning ] [ Recommender Systems ] [ Reinforcement Learning ] [ Applications - Other ]


In E-commerce, advertising is essential for merchants to reach their target users. The typical objective is to maximize the advertiser's cumulative revenue over a period of time under a budget constraint. In real applications, an advertisement (ad) usually needs to be exposed to the same user multiple times until the user finally contributes revenue (e.g., places an order). However, existing advertising systems mainly focus on the immediate revenue with single ad exposures, ignoring the contribution of each exposure to the final conversion, thus usually falls into suboptimal solutions. In this paper, we formulate the sequential advertising strategy optimization as a dynamic knapsack problem. We propose a theoretically guaranteed bilevel optimization framework, which significantly reduces the solution space of the original optimization space while ensuring the solution quality. To improve the exploration efficiency of reinforcement learning, we also devise an effective action space reduction approach. Extensive offline and online experiments show the superior performance of our approaches over state-of-the-art baselines in terms of cumulative revenue.

Chat is not available.