Ad Creative Discontinuation Prediction with Multi-Modal Multi-Task Neural Survival Networks

TL;DR

This paper introduces a multi-modal neural survival network to predict ad creative discontinuation, effectively handling short-term and long-term cases with large-scale data, outperforming traditional methods.

Contribution

The study presents a novel multi-task, multi-modal neural network framework with hazard-based loss for predicting ad discontinuation, incorporating techniques to improve accuracy for different discontinuation types.

Findings

Achieved high concordance indices (0.896, 0.939, 0.792) outperforming conventional methods.

Demonstrated comparable effectiveness to manual operations for short-term discontinuation.

Accurately predicted the order of ad discontinuation in long-term cases.

Abstract

Discontinuing ad creatives at an appropriate time is one of the most important ad operations that can have a significant impact on sales. Such operational support for ineffective ads has been less explored than that for effective ads. After pre-analyzing 1,000,000 real-world ad creatives, we found that there are two types of discontinuation: short-term (i.e., cut-out) and long-term (i.e., wear-out). In this paper, we propose a practical prediction framework for the discontinuation of ad creatives with a hazard function-based loss function inspired by survival analysis. Our framework predicts the discontinuations with a multi-modal deep neural network that takes as input the ad creative (e.g., text, categorical, image, numerical features). To improve the prediction performance for the two different types of discontinuations and for the ad creatives that contribute to sales, we introduce two new techniques: (1) a two-term estimation technique with multi-task learning and (2) a click-through rate-weighting technique for the loss function. We evaluated our framework using the large-scale ad creative dataset, including 10 billion scale impressions. In terms of the concordance index (short: 0.896, long: 0.939, and overall: 0.792), our framework achieved significantly better performance than the conventional method (0.531). Additionally, we confirmed that our framework (i) demonstrated the same degree of discontinuation effect as manual operations for short-term cases, and (ii) accurately predicted the ad discontinuation order, which is important for long-running ad creatives for long-term cases.