Home > Archive > 2019 > Volume 9 Number 3 (Jun. 2019) >
IJMLC 2019 Vol.9(3): 322-327 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2019.9.3.805

Prediction of Waiting Time in One-Stop Service

Yotravee Sanit-in and Kanda Runapongsa Saikaew

Abstract—Customers of several popular services need to wait idly for a long time. These services usually have a limited capacity and can only serve a small number of customers at a time. It is impossible for customers to receive the service without waiting at all; thus, it will be advantageous for clients to know the approximate waiting time which they may choose to do other activities instead of standing in a service queue. This article proposes and evaluates approaches to predict the waiting time before a customer receives the service. Three approaches of waiting time prediction have been implemented and compared. These approaches include Queueing Theory, Average time, and Random Forest. The experimental results indicated that the supervised learning algorithm, Random Forest, achieved the highest accuracy at 85.76% of ear nose and throat clinic dataset and 81.7% of Khon Kaen University post office dataset. This article also investigated feature importance and found that the number of waiting queues was the most critical feature in waiting time prediction.

Index Terms—Machine learning, queueing theory, random forest, waiting time prediction.

Yotravee Sanit-in and Kanda Runapongsa Saikaew are with the Faculty of Engineering, Khon Kaen University, Thailand (Corresponding author: Kanda Runapongsa Saikaew; e-mail: krunapon@kku.ac.th).


Cite: Yotravee Sanit-in and Kanda Runapongsa Saikaew, "Prediction of Waiting Time in One-Stop Service," International Journal of Machine Learning and Computing vol. 9, no. 3, pp. 322-327, 2019.

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net

Article Metrics in Dimensions