Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Call-Center Staff Scheduling Considering Performance Evolution under Emotional Stress

Yujun Zheng, Xinya Chen, Xueqin Lu, Weiguo Sheng, Shengyong Chen

TL;DR

This work tackles call-center staffing under emotional stress by introducing an emotional-stress driven working performance model that links five emotional states to performance through a Yerkes-Dodson-based framework and neuro-fuzzy estimators. It formulates a combined long-term and short-term scheduling problem and proposes MA-DQN, a memetic algorithm that couples global mutation with a DRL-guided local search to optimize duty rosters while accounting for performance evolution and impairment risk. Experimental results on real bank data show the model better predicts performance dynamics and that the proposed MA-DQN approach yields substantial scheduling improvements, highlighting the practical value of incorporating emotional factors into staffing decisions. Overall, the paper advances service level optimization by integrating human behavioral dynamics into both performance estimation and operational planning, with potential applications to other high-stress contexts.

Abstract

Emotional stress often has a significant effect on the working performance of staff, but this effect is commonly neglected in existing staff scheduling methods. We study a call-center staff scheduling problem, which considers the evolution of work performance of staff under emotional stress. First, we present an emotional stress driven model that estimates the working performance of call-center employees based on not only skill levels but also emotional states. On the basis of the model, we formulate a combined short-term and long-term call-center staff scheduling problem aiming at maximizing the customer service level, which depends on the working performance of employees. We then propose a memetic optimization algorithm combining global mutation and neighborhood search assisted by deep reinforcement learning to efficiently solve this problem. Experimental results on real-world problem instances of bank call-center staff scheduling demonstrate the performance advantages of the proposed method over selected popular staff scheduling methods. By explicitly modeling and incorporating emotional stress, our method reflects a more realistic understanding and utilization of human behavior in staff scheduling.

Call-Center Staff Scheduling Considering Performance Evolution under Emotional Stress

TL;DR

This work tackles call-center staffing under emotional stress by introducing an emotional-stress driven working performance model that links five emotional states to performance through a Yerkes-Dodson-based framework and neuro-fuzzy estimators. It formulates a combined long-term and short-term scheduling problem and proposes MA-DQN, a memetic algorithm that couples global mutation with a DRL-guided local search to optimize duty rosters while accounting for performance evolution and impairment risk. Experimental results on real bank data show the model better predicts performance dynamics and that the proposed MA-DQN approach yields substantial scheduling improvements, highlighting the practical value of incorporating emotional factors into staffing decisions. Overall, the paper advances service level optimization by integrating human behavioral dynamics into both performance estimation and operational planning, with potential applications to other high-stress contexts.

Abstract

Emotional stress often has a significant effect on the working performance of staff, but this effect is commonly neglected in existing staff scheduling methods. We study a call-center staff scheduling problem, which considers the evolution of work performance of staff under emotional stress. First, we present an emotional stress driven model that estimates the working performance of call-center employees based on not only skill levels but also emotional states. On the basis of the model, we formulate a combined short-term and long-term call-center staff scheduling problem aiming at maximizing the customer service level, which depends on the working performance of employees. We then propose a memetic optimization algorithm combining global mutation and neighborhood search assisted by deep reinforcement learning to efficiently solve this problem. Experimental results on real-world problem instances of bank call-center staff scheduling demonstrate the performance advantages of the proposed method over selected popular staff scheduling methods. By explicitly modeling and incorporating emotional stress, our method reflects a more realistic understanding and utilization of human behavior in staff scheduling.
Paper Structure (18 sections, 7 equations, 13 figures, 6 tables, 1 algorithm)

This paper contains 18 sections, 7 equations, 13 figures, 6 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Emotional Stress Driven Working Performance Model
  4. Basic Law of Arousal Effects on Performance
  5. Short-Term Working Performance
  6. Long-Term Working Performance
  7. Combined Short- and Long-Term Customer Service Scheduling Optimization Problem
  8. Memetic Optimization Algorithm
  9. Solution Initialization
  10. Global Mutation for Long-Term Scheduling
  11. Variable Neighborhood Search for Short-Term Scheduling
  12. Deep Reinforcement Learning for Neighborhood Search
  13. Constraint Handling
  14. Algorithm Framework
  15. Experiments
  16. ...and 3 more sections

Figures (13)

  • Figure 1: Schematic representation of the hypothalamic-pituitary–adrenal (HPA) axis Lupien07BrainCog.
  • Figure 2: Curvilinear relationship between stress and performance (from https://delphis.org.uk/peak-performance).
  • Figure 3: Different arousal effects on performance under easy and hard situations.
  • Figure 4: Different arousal effects on performance under easy and hard situations.
  • Figure 5: Service request cancellation rate with time.
  • ...and 8 more figures