GTC Silicon Valley-2019: Improving Customer Service with Deep Learning Techniques in a Multi-Touchpoint System
GTC Silicon Valley-2019 ID:S9311:Improving Customer Service with Deep Learning Techniques in a Multi-Touchpoint System
Rajesh Munavalli(PayPal, Inc)
We'll present our work on unified models leveraging both deep learning and traditional modeling techniques to improve customer service in a multi-touchpoint system. A typical business has more than 20 direct and indirect multi-modal touchpoints. Forming a unified view of these interactions is critical in giving a smooth end-to-end consistent experience. By combining both structured and unstructured data, we can resolve many customer issues even before there is a need for them to contact the business. To address this and mitigate overall customer contact rates, we have built a suite of solutions with chatbots, email routing and auto-response solutions.