Ad creative generation using reinforced generative adversarial network

Abstract

Crafting the right keywords and crafting their ad creatives is an arduous task that requires the collaboration of online marketers, creative directors, data scientists, and possibly linguists. Many parts of this craft are still manual and therefore not scalable especially for large e-commerce companies that have big inventories and big search campaigns. Furthermore, the craft is inherently experimental, which means that the marketing team has to experiment with different marketing messages from subtle to strong, with different keywords from broadly relevant (to the product) to exactly/specifically relevant, with different landing pages from informative to transactional, and many other test variants. The failure to experiment quickly for finding what works results in users being dissatisfied and marketing budget being wasted. For rapid experimentation, we set out to generate ad creatives automatically. The process of generating an ad creative from a given landing page is considered as a text summarization problem and we adopted the abstractive text summarization approach. We reported the results of our empirical evaluation on generative adversarial networks and reinforcement learning methods.