Adaptive Call Center Workforce Management With Deep Neural Network and Reinforcement Learning

Abstract

Workforce management is one of several critical issues in a call center. A call center supervisor must assign an adequate number of call agents to handle a high volume of time-variant incoming calls. Without effective staff allocation, improper workforce management can degrade service quality and reduce customer satisfaction. This paper presents a novel call center workforce management based on a deep neural network and reinforcement learning (RL). The proposed method first uses a deep neural network to learn and predict call center traffic characteristics. The deep neural network consists of a Long-Short Term Memory (LSTM) network and a Deep Neural Network (DNN) capturing non-linear call traffic behaviors. The expected traffic parameters are supplied into the Erlang A model, which calculates important service metrics, including a call abandonment probability and the average response time. This paper applies a reinforcement learning framework using the Q-learning algorithm to establish the optimal starting times of call agent shifts and their associated call agent numbers by maximizing a defined reward function to handle dynamic call center traffic. The objective of these findings is to maintain the quality of service of a call center throughout working hours. The proposed method surpasses experienced human supervisors and previous workforce management schemes in terms of achieved qualities of service and average waiting time from experimental results under actual call center data.

Customer Service Combining Human Operators and Virtual Agents: A Call for Multidisciplinary AI Research

“…The issue of task allocation and staff allocation (sometimes called workforce management) is of great importance to call centers. It was approached with methods of queuing theory in (Bouchentouf, Cherfaoui, and Boualem 2021) (OR), with deep neural networks and reinforcement learning in (Kumwilaisak et al 2022) (RL), and various other methods (Cohen, Reis, and Amorim 2020) (OR), (Horng and Lin 2020) (informatics, social science). Allocation of tasks in cases where there are operators with two levels of expertise, as our model may be described, is discussed in (Stepanov, Stepanov, and Zhurko 2019) (OR).…”

Path Following and Avoiding Obstacle for Mobile Robot Under Dynamic Environments Using Reinforcement Learning

“…The intelligent control needs data or experience to design [51][52]. Reinforcement learning (RL), unlike other artificial intelligence algorithms, is a learning method that does not require any rules [53][54][55][56]. RL is a machine learning method that regards the feedback of the environment as an input and adapts the environment.…”

Principle Operation of a Line Follower Robot

“…Designing an intelligent control requires knowledge or experience [38][39]. Contrary to other artificial intelligence algorithms, reinforcement learning (RL) is a learning technique that doesn't need any rules [40][41][42][43]. RL is a machine learning technique that modifies the environment by using the environment's feedback as an input.…”