Publicação
Hospitality AI-Driven Customer Journey Analytics: Predicting touchpoints in hotel Customer Journeys
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | pt_PT |
| dc.contributor.advisor | Neto, Miguel de Castro Simões Ferreira | |
| dc.contributor.advisor | Jardim, João Bruno Morais de Sousa | |
| dc.contributor.author | Rodrigues, Duarte Nuno Antunes Caracol Barros | |
| dc.date.accessioned | 2024-03-22T18:40:32Z | |
| dc.date.available | 2024-03-22T18:40:32Z | |
| dc.date.issued | 2024-02-07 | |
| dc.description | Project Work presented as the partial requirement for obtaining a Master's degree in Data Driven Marketing, specialization in Marketing Intelligence | pt_PT |
| dc.description.abstract | The goal of this project is to develop a Customer Journey Framework that enables the marketing department of two hotels, a resort hotel (H1) and a city hotel (H2), to predict guest’s behaviour using classification models throughout the three phases of their journey, Pre-Service, Service and Post-Service, using data obtained from the reservation management system. The marketing department can use the predictions to improve each guest’s stay by anticipating the best outcome at each of these phases for each guest and start a conversation, creating opportunities to improve the service provided to guests while also improving the bottom-line results of the hotel at very little cost. It expands on work developed by Andriawan et al. (2020) and Antonio, Almeida, et al. (2017), who successfully developed classification models to predict cancellations using tree-based algorithms, by increasing the prediction scope to a full CJ in a hotel, building and testing separate models, divided per hotel, with each model answering each research question. The first model predicts the cancellation of bookings, scoring a recall above 80% in both hotels, the second model predicts the food and beverage package, scoring a F1 Score of 66% at H1 and 85% at H2, lastly the third model predicts which guests will book another stay, scoring a recall above 90% in both hotels. | pt_PT |
| dc.identifier.tid | 203553535 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10362/165307 | |
| dc.language.iso | eng | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Hospitality | pt_PT |
| dc.subject | Customer journey | pt_PT |
| dc.subject | Touchpoints | pt_PT |
| dc.subject | Machine Learning | pt_PT |
| dc.subject | AI | pt_PT |
| dc.subject | Classification | pt_PT |
| dc.subject | XGBoost | pt_PT |
| dc.subject | SDG 9 - Industry, innovation and infrastructure | pt_PT |
| dc.title | Hospitality AI-Driven Customer Journey Analytics: Predicting touchpoints in hotel Customer Journeys | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | Mestrado em Marketing Analítico, especialização em Inteligência de Marketing | pt_PT |