Optimizing email marketing campaigns in the airline industry using knowledge graph embeddings

The use of email marketing campaigns in e-commerce is an essential aspect for driving sales and establishing or maintaining good customer service. However, ensuring their success in the airline industry is challenging, and the risk is high that the marketing campaign content is not suited to the needs of specific travelers. The traveler may rapidly feel spammed and the offer content promoted via emails may even be no longer accessed. Consequently, the use of personalised recommender systems for email marketing campaigns becomes essential to build user loyalty and to increase offer conversion. Recently, the use of knowledge graphs has proven to be an effective way to recommend products. In this work, we propose an approach that leverages knowledge graph embeddings to better target the right audience in email marketing campaigns for airline

products recommendation. We conduct extensive experiments to compare our approach with the currently in-production rule-based system used by airline marketers and a supervised machine learning model based on handcrafted features as another baseline. The

results suggest that the use of knowledge graph embeddings is the most effective approach.