Ruofeng Wen

Ruofeng Wen, Wenjun Zeng, Yi Liu

Amazon Customer Service provides real-time support for millions of customer contacts every year. While bot-resolver helps automate some traffic, we still see high demand for human agents, also called subject matter experts (SMEs). Customers outreach with questions in different domains (return policy, device troubleshooting, etc.). Depending on their training, not all SMEs are eligible to handle all contacts. Routing contacts to eligible SMEs turns out to be a non-trivial problem because SMEs' domain eligibility is subject to training quality and can change over time. To optimally recommend SMEs while simultaneously learning the true eligibility status, we propose to formulate the routing problem with a nonparametric contextual bandit algorithm (K-Boot) plus an eligibility control (EC) algorithm. K-Boot models reward with a kernel smoother on similar past samples selected by $k$-NN, and Bootstrap Thompson Sampling for exploration. EC filters arms (SMEs) by the initially system-claimed eligibility and dynamically validates the reliability of this information. The proposed K-Boot is a general bandit algorithm, and EC is applicable to other bandits. Our simulation studies show that K-Boot performs on par with state-of-the-art Bandit models, and EC boosts K-Boot performance when stochastic eligibility signal exists.

Ruofeng Wen

We developed a machine learning approach that quantifies multiple aspects of the success or values in Customer Service contacts, at anytime during the interaction. Specifically, the value/reward function regarding to the turn-level behaviors across human agents, chatbots and other hybrid dialog systems is characterized by the incremental information and confidence gain between sentences, based on the token-level predictions from a multi-task neural network trained with only weak signals in dialog-level attributes/states. The resulting model, named Value Profiler, serves as a goal-oriented dialog manager that enhances conversations by regulating automated decisions with its reward and state predictions. It supports both real-time monitoring and scalable offline customer experience evaluation, for both bot- and human-handled contacts. We show how it improves Amazon customer service quality in several applications.