University of British Columbia
The value of text for waiting time prediction using deep learning : a repair shop case study
Abstract
dc:descriptionOne of the most formidable tasks for service companies is to inform customers about the approximate waiting time. Overestimated waiting time may force customers not to proceed with a company, and underestimated waiting time may lead to an impossible responsibility for the company to accomplish. In both cases, customer dissatisfaction would occur. To tackle this challenge, we propose a two-phase predictive model using textual combined with structured data to predict waiting time in service systems. In the first phase, the Bag of Words as a text mining approach is utilized to transform texts into numbers. In the second phase, based on nearly 31,000 case study data, our work exploits a Multi-Layer Perceptron architecture from deep learning as the best predictive model for a regression task. Our numerical results show that deep learning by having 87.6% accuracy has the best performance compared to conventional machine learning algorithms for predicting a continuous output based on textual data. Our numerical results demonstrate that deep learning outperforms traditional machine learning algorithms in predicting continuous outputs from textual data, achieving an accuracy of 87.6%. Additionally, our study highlights the importance of textual data in predicting wait times. We found that using only textual data enhances prediction accuracy by 3.6%. Moreover, the most accurate results, showing a 5.3% improvement, were obtained when combining structured and textual data. Finally, we demonstrate that our predictive model can assist experts' decisions in underestimated waiting time cases by improving 50.1% accuracy from 31.75% to 81.87%. Also, from the managerial perspective, we illustrate how textual data are vital in terms of descriptive analysis to find deficiencies in a service system.
Degree
thesis:*- Name thesis:degree_name
- Master of Science - MSc
- Level thesis:degree_level
- master's
- Discipline thesis:degree_discipline
- Mathematics
- Grantor dc:publisher
- University of British Columbia
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Mosaffa, Mohammad
- Contributors dc:contributor
-
- Tavakoli, Javad
Rights
dc:rights- Statement dc:rights
-
- Attribution-ShareAlike 4.0 International
- Language dc:language
- eng
Identifiers
dc:identifier.*- Handle dc:identifier
- http://hdl.handle.net/2429/85967