2560. Data-driven Stochastic Optimization for Mental Health Crisis Call Center Scheduling
Invited abstract in session WA-11: Resource and treatment planning, stream OR in Healthcare (ORAHS).
Wednesday, 8:30-10:00Room: Clarendon SR 1.03
Authors (first author is the speaker)
| 1. | Shenghan Xu
|
| Business, University of Idaho | |
| 2. | Alireza Boloori
|
| Milgard School of Business, University of Washington |
Abstract
Efficient scheduling and capacity planning are essential for mental health crisis call centers to handle the rising demand for timely and effective support. This study addresses resource allocation challenges by introducing a two-stage stochastic programming model to optimize operator assignments. It aims to bridge the gap between fluctuating demand and the need for consistent service quality, focusing on mental health crisis intervention where accessibility and responsiveness are crucial.
The study explores balancing operational efficiency with high service levels under uncertainty in call arrival rates and diverse patient needs. The proposed model incorporates real-world demand data, simulating various scenarios to capture call volume and service time uncertainties. A 90% call answer rate is a benchmark to ensure accessibility and customer satisfaction while integrating cost considerations to align with organizational goals.
Through comprehensive data analysis and scenario testing, results show that stochastic programming enables effective resource allocation despite fluctuating demand. Key contributions include a robust decision-support framework for scheduling under uncertainty while maintaining efficiency.
Keywords
- Health Care
- Analytics and Data Science
- Service Operations
Status: accepted
Back to the list of papers