Cross-Element Combinatorial Selection for Multi-Element Creative in Display Advertising

TL;DR

This paper introduces CECS, a novel framework for selecting multi-element ad creatives by modeling interactions among elements, leading to improved effectiveness and significant business gains.

Contribution

It proposes a cross-element interaction framework and cascade selection mechanism for multi-element creative selection, addressing limitations of independent element selection.

Findings

Achieved state-of-the-art offline metric scores.

Deployed in industry with 6.02% CTR lift.

Real-world application showed 10.37% GMV increase.

Abstract

The effectiveness of ad creatives is greatly influenced by their visual appearance. Advertising platforms can generate ad creatives with different appearances by combining creative elements provided by advertisers. However, with the increasing number of ad creative elements, it becomes challenging to select a suitable combination from the countless possibilities. The industry's mainstream approach is to select individual creative elements independently, which often overlooks the importance of interaction between creative elements during the modeling process. In response, this paper proposes a Cross-Element Combinatorial Selection framework for multiple creative elements, termed CECS. In the encoder process, a cross-element interaction is adopted to dynamically adjust the expression of a single creative element based on the current candidate creatives. In the decoder process, the creative combination problem is transformed into a cascade selection problem of multiple creative elements. A pointer mechanism with a cascade design is used to model the associations among candidates. Comprehensive experiments on real-world datasets show that CECS achieved the SOTA score on offline metrics. Moreover, the CECS algorithm has been deployed in our industrial application, resulting in a significant 6.02% CTR and 10.37% GMV lift, which is beneficial to the business.