Attention Fusion Networks: Combining Behavior and E-mail Content to Improve Customer Support
This work addresses customer support efficiency for companies like Square, but it is incremental as it combines existing data sources with standard deep learning methods.
The paper tackled the problem of improving customer support by predicting the most relevant solution to seller inquiries, achieving better performance than models using only a single data source.
Customer support is a central objective at Square as it helps us build and maintain great relationships with our sellers. In order to provide the best experience, we strive to deliver the most accurate and quasi-instantaneous responses to questions regarding our products. In this work, we introduce the Attention Fusion Network model which combines signals extracted from seller interactions on the Square product ecosystem, along with submitted email questions, to predict the most relevant solution to a seller's inquiry. We show that the innovative combination of two very different data sources that are rarely used together, using state-of-the-art deep learning systems outperforms, candidate models that are trained only on a single source.