Lessons from Contextual Bandit Learning in a Customer Support Bot
This work provides incremental insights for practitioners implementing reinforcement learning in customer support systems.
The authors tackled the challenge of applying contextual bandits to improve business metrics in a customer support bot, sharing practical lessons and solutions for issues encountered in real-world applications.
In this work, we describe practical lessons we have learned from successfully using contextual bandits (CBs) to improve key business metrics of the Microsoft Virtual Agent for customer support. While our current use cases focus on single step einforcement learning (RL) and mostly in the domain of natural language processing and information retrieval we believe many of our findings are generally applicable. Through this article, we highlight certain issues that RL practitioners may encounter in similar types of applications as well as offer practical solutions to these challenges.