Advanced search
1 file | 12.15 KB Add to list

Gaussian processes for daily demand prediction in the hospitality industry

Wai Tsang (UGent) and Dries Benoit (UGent)
Author
Organization
Abstract
In tourism forecasting literature, the majority of the studies relies on econometric models. While econometric models are effective for monthly or yearly data, many machine learning techniques are yet to be explored in the demand literature and it can be beneficial to do so on daily data. This study fills the research gap by predicting daily hotel occupancy rates on a city level in Brussels using booking.com data. A forecasting methodology is proposed with feature extraction and selection, processing steps that are missing in most approaches. Special attention is given to Gaussian Processes to make predictions with credible intervals, an uncertainty measure that is helpful for managers during decision-making. The novel approach uses online data to create a proxy measure for occupancy rate. The new methodology is verified with internal occupancy data from hotels in Brussels and can be extrapolated to cities for which no internal hotel data is available.

Downloads

  • (...).docx
    • full text
    • |
    • UGent only
    • |
    • Word
    • |
    • 12.15 KB

Citation

Please use this url to cite or link to this publication:

MLA
Tsang, Wai, and Dries Benoit. “Gaussian Processes for Daily Demand Prediction in the Hospitality Industry.” EURO 2018 : Meeting Abstracts, 2018.
APA
Tsang, W., & Benoit, D. (2018). Gaussian processes for daily demand prediction in the hospitality industry. In EURO 2018 : meeting abstracts. Valencia, Spain.
Chicago author-date
Tsang, Wai, and Dries Benoit. 2018. “Gaussian Processes for Daily Demand Prediction in the Hospitality Industry.” In EURO 2018 : Meeting Abstracts.
Chicago author-date (all authors)
Tsang, Wai, and Dries Benoit. 2018. “Gaussian Processes for Daily Demand Prediction in the Hospitality Industry.” In EURO 2018 : Meeting Abstracts.
Vancouver
1.
Tsang W, Benoit D. Gaussian processes for daily demand prediction in the hospitality industry. In: EURO 2018 : meeting abstracts. 2018.
IEEE
[1]
W. Tsang and D. Benoit, “Gaussian processes for daily demand prediction in the hospitality industry,” in EURO 2018 : meeting abstracts, Valencia, Spain, 2018.
@inproceedings{8618211,
  abstract     = {In tourism forecasting literature, the majority of the studies relies on econometric models. While econometric models are effective for monthly or yearly data, many machine learning techniques are yet to be explored in the demand literature and it can be beneficial to do so on daily data. This study fills the research gap by predicting daily hotel occupancy rates on a city level in Brussels using booking.com data. A forecasting methodology is proposed with feature extraction and selection, processing steps that are missing in most approaches. Special attention is given to Gaussian Processes to make predictions with credible intervals, an uncertainty measure that is helpful for managers during decision-making. The novel approach uses online data to create a proxy measure for occupancy rate. The new methodology is verified with internal occupancy data from hotels in Brussels and can be extrapolated to cities for which no internal hotel data is available.},
  author       = {Tsang, Wai and Benoit, Dries},
  booktitle    = {EURO 2018 : meeting abstracts},
  language     = {eng},
  location     = {Valencia, Spain},
  title        = {Gaussian processes for daily demand prediction in the hospitality industry},
  year         = {2018},
}