- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- The value of text for waiting time prediction using...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
The value of text for waiting time prediction using deep learning : a repair shop case study Mosaffa, Mohammad
Abstract
One 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.
Item Metadata
| Title |
The value of text for waiting time prediction using deep learning : a repair shop case study
|
| Creator | |
| Supervisor | |
| Publisher |
University of British Columbia
|
| Date Issued |
2023
|
| Description |
One 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.
|
| Genre | |
| Type | |
| Language |
eng
|
| Date Available |
2023-09-19
|
| Provider |
Vancouver : University of British Columbia Library
|
| Rights |
Attribution-ShareAlike 4.0 International
|
| DOI |
10.14288/1.0435924
|
| URI | |
| Degree | |
| Program | |
| Affiliation | |
| Degree Grantor |
University of British Columbia
|
| Graduation Date |
2023-09
|
| Campus | |
| Scholarly Level |
Graduate
|
| Rights URI | |
| Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-ShareAlike 4.0 International