CEU Electronic Theses and Dissertations, 2020
| Author | Miranda, Rolibeth Arielle Ramos |
|---|---|
| Title | Predicting Waiting Time Duration in Digital Queues |
| Summary | Linistry is a disruptive queue management solution offered to companies with customer service offices and branch networks like banks, telekom companies, retail stores or even large events. With Linistry, people can join a queue virtually, from any location, book an appointment, or request a ticket on-sight via a digital, paperless kiosk. Paramount to a better customer experience is the ability to forecast waiting time. AI and Machine Learning solutions to predict waiting time are being explored to replace the current calculation methods being used. The goal is to build a model that can give more accurate predictions of waiting time, factoring in the data from Linistry such as historical transactions, information and attributes of clients, and other available data. After building the model, the estimated waiting time range will be optimized. The overall goal is to have high percentage of “correct predictions” (transactions with actual waiting time falling within the estimated time frame). |
| Supervisor | Daróczi, Gergely |
| Department | Economics MSc |
| Full text | https://www.etd.ceu.edu/2020/miranda_rolibeth.pdf |
Visit the CEU Library.
© 2007-2021, Central European University