Machine Learning Applied to Walk-in Demand Prediction of a University Counseling Center


  • Erin Magee University of Florida
  • Meserret Karaca University of Florida
  • Michelle Alvarado University of Florida
  • Ernesto Escoto University of Florida
  • Alvin Lawrence University of Florida



counseling, machine learning, demand prediction, appointments


University of Florida Counseling and Wellness Center (UF CWC) is one of the counseling centers that implemented a walk-in appointment policy for emergency needs. The attendance to UF CWC has increased in walk-in appointment traffic every year since data collection began in 2010, averaging a 7% increase in patient visits per year. However, demand for walk-in services is highly uncertain on an hourly, daily or weekly basis. Additionally, emergency needs of students should be met immediately before they become a catastrophic event. Thus, demand prediction becomes an important aspect to dynamically schedule counselors to deal with unexpected demand scenarios.  This project provides data visualization and utilizes machine learning techniques to predict future demand to assist with scheduling. We identified seasonal trends in historical visit data from the center, including peaks at the beginning of semesters and around finals. We then used the visit data to train a Gradient Boosting algorithm to predict demand. This model predicted demand with a mean of 4.2 patients per hour and mean square error of 1.75. Our results contribute to better demand prediction models for the UF CWC so that they may better support student needs with adequate staffing levels.

Author Biographies

Erin Magee, University of Florida

Industrial and Systems Engineering

Undergraduate Student

Meserret Karaca, University of Florida

Industrial and Systems Engineerin

Ph.D. Student

Michelle Alvarado, University of Florida

Industrial and Systems Engineering

Assistant Professor

Ernesto Escoto, University of Florida

Counseling and Wellness Center


Alvin Lawrence, University of Florida

Counseling and Wellness Center

Associate Director/Clinical Director


Bard, J. F., & Purnomo, H. W. (2005). Short-Term Nurse Scheduling in Response to Daily Fluctuations in Supply and Demand. Health Care Management Science,8(4), 315-324. doi:10.1007/s10729-005-4141-9

Becker, T., Steenweg, P. M., & Werners, B. (2018). Cyclic shift scheduling with on-call duties for emergency medical services. Health Care Management Science. doi:10.1007/s10729-018-9451-9

Bouquin, D. (2018, December 7). Stochastic Gradient Boosting Machines: The basics. Retrieved March 22, 2019, from

Gorman, B. (2017, January 24). A Kaggle Master Explains Gradient Boosting. Retrieved from

Hong, W. S., Haimovich, A. D., & Taylor, R. A. (2018). Predicting hospital admission at emergency department triage using machine learning. Plos One,13(7). doi:10.1371/journal.pone.0201016

Parr, T., & Howard, J. (n.d.). How to explain gradient boosting. Retrieved from

Shaffer, K. S., Love, M. M., Chapman, K. M., Horn, A. J., Haak, P. P., & Shen, C. Y. (2016). Walk-In Triage Systems in University Counseling Centers. Journal of College Student Psychotherapy,31(1), 71-89. doi:10.1080/87568225.2016.1254005

Sherali, H. D., Ramahi, M. H., & Saifee, Q. J. (2002). Hospital resident scheduling problem. Production Planning & Control,13(2), 220-233. doi:10.1080/09537280110069667

The Best Education Schools for Student Counseling and Personnel Services, Ranked. (n.d.). Retrieved from

Watkins, D. C., Hunt, J. B., & Eisenberg, D. (2011). Increased demand for mental health services on college campuses: Perspectives from administrators. Qualitative Social Work: Research and Practice,11(3), 319-337. doi:10.1177/1473325011401468

Wiler, J. L., Griffey, R. T. & Olsen, T. (2011), Review of Modeling Approaches for Emergency Department Patient Flow and Crowding Research. Academic Emergency Medicine, 18: 1371-1379. doi:10.1111/j.1553-2712.2011.01135.x