Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure

TL;DR

This paper introduces an adaptive, tree-structured framework for efficiently selecting the best ad creatives in online advertising, leveraging dynamic programming and Thompson sampling to improve click-through rate estimation and optimization.

Contribution

It proposes a novel tree-structured adaptive selection framework that combines dynamic programming with Thompson sampling to efficiently optimize ad creative selection under feedback sparsity.

Findings

Outperforms baseline methods in convergence rate

Achieves higher overall CTR in experiments

Effective in both synthetic and real-world datasets

Abstract

Ad creatives are one of the prominent mediums for online e-commerce advertisements. Ad creatives with enjoyable visual appearance may increase the click-through rate (CTR) of products. Ad creatives are typically handcrafted by advertisers and then delivered to the advertising platforms for advertisement. In recent years, advertising platforms are capable of instantly compositing ad creatives with arbitrarily designated elements of each ingredient, so advertisers are only required to provide basic materials. While facilitating the advertisers, a great number of potential ad creatives can be composited, making it difficult to accurately estimate CTR for them given limited real-time feedback. To this end, we propose an Adaptive and Efficient ad creative Selection (AES) framework based on a tree structure. The tree structure on compositing ingredients enables dynamic programming for efficient ad creative selection on the basis of CTR. Due to limited feedback, the CTR estimator is usually of high variance. Exploration techniques based on Thompson sampling are widely used for reducing variances of the CTR estimator, alleviating feedback sparsity. Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR. We finally evaluate the proposed algorithm on the synthetic dataset and the real-world dataset. The results show that our approach can outperform competing baselines in terms of convergence rate and overall CTR.