Time series forecast of call volume in VNPT call center | |
| Author | Nguyen Khanh Toan |
| Call Number | AIT Project no.PMDS-22-01 |
| Subject(s) | Time-series analysis--Data processing Call centers--Vietnam--Data processing Deep learning (Machine learning) |
| Note | A project study submitted in partial fulfillment of the requirements for the degree of Professional Master in Data Science and Artificial Intelligence Applications, |
| Publisher | Asian Institute of Technology |
| Series Statement | Project ; no. PMDS-22-01 |
| Abstract | A collection of points that have been collected at regular intervals over time is called a time series. Analysis of time series investigates time correlations and attempts to model them according to trend and seasonality. Forecasting future values, which is considered fundamental in numerous real-world scenarios, is one of the most significant tasks in time series analysis. Currently, many businesses forecast using hand-written models or naive statistical models. Call centers are the organization's initial point of contact with customers, managing the relationship with them. The forecasting of call volume and the optimization of the schedule continue to be crucial obstacles for call centers. Deep learning has been applied to several fields with excellent results, and time series forecasting problems have recently gained popularity thanks to the new recurrent network known as LSTM. This thesis investigated the capabilities of deep learning in modeling and forecasting call load time series with strong seasonality at the daily and hourly scales. The primary metric used to evaluate the results is the MSE, which is used to calculate the model's accuracy. We conducted our experiments using data from the VNPT call center. The experimental results show that LSTM is more accurate in forecasting at the hourly scale, but none of the methods are effective at the daily scale due to a lack of data samples. |
| Year | 2022 |
| Corresponding Series Added Entry | Asian Institute of Technology. Project ; no. PMDS-22-01 |
| Type | Project |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Professional Master in Data Science and Artificial Intelligence Applications (PMDS) |
| Chairperson(s) | Cherdsak Kingkan; |
| Examination Committee(s) | Chutiporn Anutariya;Vatcharaporn Esichaikul; |
| Degree | Professional Master in Data Science and Artificial Intelligence Applications - Asian Institute of Technology, 2022 |