Exploring the use of predictive analytics in reducing customer wait time in a college cafeteria
Date
2016-04
item.page.datecreated
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Predictive analytics, is a practice of extracting information from existing data sets
in order to predict outcome and trends in the future. Techniques of predictive analytics
such as data mining, statistics, modelling and machine learning are used extensively in the
hospitality industry for predicting customer frequency, wait time, crop yields among
others. For the purpose of this paper, we will be exploring the influence of forecasted data
in reducing wait time at a college cafeteria, using modelling as the predictive analytics
technique.
Cafeterias provide meals and drinks to specific target groups of customers
especially in schools, hospitals, organizations and companies at a charge. They are mainly
different from the other food service providers in terms of their service styles, whereby
there is no waiting staff but rather the customer serves from a buffets of meals and pays
for meals by themselves. Due to this serving style, there is a challenge of preventing long
queues and reducing wait time for customers to pick up food. An increase in wait time for
customers could lead to customer dissatisfaction and this paper seeks to address this
challenge.
The objective of this study is to assess the impact of a predictive model in reducing
the wait time at a cafeteria. To achieve this objective, a mathematical model is formulated
to accurately predict the number of customers likely to visit the cafeteria at various times
during the day. The impact of the predictions is then assessed in its ability to reduce wait
time.
Description
Thesis submitted to the Department of Computer Science, Ashesi University College, in partial fulfillment of Bachelor of Science degree in Computer Science, April 2016
item.page.type
Thesis
item.page.format
Keywords
predictive analytics, Ghana, Ashesi University College, cafeteria, customer satisfaction