Contribution analysis of video advertising with topic model and ensemble learning

Abstract

With the widespread use of highly functional smartphones and the improvement of communication environments, video advertising is becoming widely used in the mobile advertising domain. When creators create video advertisements, if they know in advance the most effective components and combinations, they are more likely to be able to produce them more efficiently. For mobile ad images, [Sakihama 19b] interpreted the results of a click-rate prediction model using Gradient Boosted Decision Trees (GBDT) and Interpretable Trees (inTrees) [Deng 19]. In this paper, we propose a multimodal approach to analyzing the factors of advertising effectiveness, which consists of ad delivery logs, components of video ads, and text information. Specifically, we propose a method for verifying the effectiveness of video advertisements in mobile advertising based on computer vision and a method for supporting the production of video advertisements using the modeling results of Latent Dirichlet Allocation (LDA), XgBoost [Chen 16], and defragTrees [Hara 18]. This method is expected to be faster and simpler than the one proposed by [Sakihama 19b], and is likely to enable rule extraction. Computer vision and machine learning will enable automatic feature extraction, identification of effective components and interactions, and contribution measurement. It is expected to be applied to a wide range of fields other than video advertising.