Estimating Individual Advertising Effect in E-Commerce

TL;DR

This paper models individual advertising effects in e-commerce using causal inference with multiple treatments, enabling more effective bidding strategies that improve overall advertising returns, including indirect effects.

Contribution

It introduces a causal inference framework for estimating individual advertising effects with multiple treatments, optimizing online bidding strategies in real-world systems.

Findings

Causal effect modeling improves bidding performance.

Online experiments show superior results over existing algorithms.

Effective estimation reduces advertising costs and enhances returns.

Abstract

Online advertising has been the major monetization approach for Internet companies. Advertisers invest budgets to bid for real-time impressions to gain direct and indirect returns. Existing works have been concentrating on optimizing direct returns brought by advertising traffic. However, indirect returns induced by advertising traffic such as influencing the online organic traffic and offline mouth-to-mouth marketing provide extra significant motivation to advertisers. Modeling and quantization of causal effects between the overall advertising return and budget enable the advertisers to spend their money more judiciously. In this paper, we model the overall return as individual advertising effect in causal inference with multiple treatments and bound the expected estimation error with learnable factual loss and distance of treatment-specific context distributions. Accordingly, a representation and hypothesis network is used to minimize the loss bound. We apply the learned causal effect in the online bidding engine of an industry-level sponsored search system. Online experiments show that the causal inference based bidding outperforms the existing online bidding algorithm.