Access Type

Open Access Thesis

Date of Award

January 2011

Degree Type

Thesis

Degree Name

M.S.

Department

Computer Science

First Advisor

Chandan K. Reddy

Abstract

In spite of the success of theoretical appointment scheduling methods, there have been significant failures in practice primarily due to the rapid increase in the number of no-shows and cancelations from the individuals in recent times. These disruptions not only cause inconvenience to the management but also has a significant impact on the revenue, cost and resource utilization. In this research, we develop a hybrid probabilistic model based on logistic regression and Bayesian inference to predict the probability of no-shows in real-time. We also develop two novel non-sequential and sequential optimization models which can effectively use no-show probabilities for scheduling patients. Our integrated prediction and optimization model can be used to enable a precise overbooking strategy to reduce the negative effect of no-shows and fill appointment slots while maintaining short wait times. Using both simulated and real-world data, we demonstrate the effectiveness of the proposed hybrid predictive model and scheduling strategy compared to some of the well-studied approaches available in the literature.