A General Traffic Shaping Protocol in E-Commerce

TL;DR

This paper introduces a general online traffic shaping protocol for E-Commerce that reduces dependence on accurate utility prediction models by approximating the relationship between bonus scores and exposures using piece-wise linear functions, formulated as a linear programming problem, and validated through online A/B testing.

Contribution

It proposes a novel traffic shaping framework that approximates utility functions with piece-wise linear functions and formulates the problem as linear programming, improving robustness and performance.

Findings

Outperforms existing traffic shaping algorithms in online A/B tests.

Effectively approximates utility functions without relying on precise conversion rate models.

Provides a scalable and flexible traffic shaping solution for E-Commerce platforms.

Abstract

To approach different business objectives, online traffic shaping algorithms aim at improving exposures of a target set of items, such as boosting the growth of new commodities. Generally, these algorithms assume that the utility of each user-item pair can be accessed via a well-trained conversion rate prediction model. However, for real E-Commerce platforms, there are unavoidable factors preventing us from learning such an accurate model. In order to break the heavy dependence on accurate inputs of the utility, we propose a general online traffic shaping protocol for online E-Commerce applications. In our framework, we approximate the function mapping the bonus scores, which generally are the only method to influence the ranking result in the traffic shaping problem, to the numbers of exposures and purchases. Concretely, we approximate the above function by a class of the piece-wise linear function constructed on the convex hull of the explored data points. Moreover, we reformulate the online traffic shaping problem as linear programming where these piece-wise linear functions are embedded into both the objective and constraints. Our algorithm can straightforwardly optimize the linear programming in the prime space, and its solution can be simply applied by a stochastic strategy to fulfill the optimized objective and the constraints in expectation. Finally, the online A/B test shows our proposed algorithm steadily outperforms the previous industrial level traffic shaping algorithm.