Recurrent and decomposed neural network-based hotel occupancy forecasting

Hyung Rim Choi, Wooju Kim, Sung Youn An

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Occupancy forecasting is one of the most important decisions a hotel's management must make. If a more accurate form of forecasting is available, the hotel managers can increase their profits through the efficient management of rooms based on the forecasts. However, there are two major problems in applying the traditional time series model to hotel occupancy forecasting. One of the reasons is due to the upper and lower bounds which exist in the hotel occupancy data. The other is that there are many judgmental and exogenous factors which strongly affect the hotel occupancy. However, it is difficult to consider these factors in the forecasting model by using a time series model or causal model. Therefore, a recurrent and decomposed neural network-based hotel occupancy forecasting model has been proposed to resolve such problems. To validate our proposed neural network model, experiments have been performed using the real world data from a hotel. Based on the experiment's results, the proposed neural network model outperforms not only the ARIMA approach, but also other possible neural network models. This study also includes an interesting discussion about the issues that should be considered in applying a neural network to the forecasting domain through various comparative experiments between the time series model and the neural network, and among various types of neural networks.

Original languageEnglish
Pages (from-to)121-136
Number of pages16
JournalNew Review of Applied Expert Systems and Emerging Technologies
Volume3
Publication statusPublished - 1997 Dec 1

Fingerprint

Hotels
Neural networks
Time series
Experiments
Profitability
Managers
Network model
Time series models
Experiment

All Science Journal Classification (ASJC) codes

  • Management of Technology and Innovation

Cite this

@article{1b6c7ed8793f43c5881bad8eccf956d5,
title = "Recurrent and decomposed neural network-based hotel occupancy forecasting",
abstract = "Occupancy forecasting is one of the most important decisions a hotel's management must make. If a more accurate form of forecasting is available, the hotel managers can increase their profits through the efficient management of rooms based on the forecasts. However, there are two major problems in applying the traditional time series model to hotel occupancy forecasting. One of the reasons is due to the upper and lower bounds which exist in the hotel occupancy data. The other is that there are many judgmental and exogenous factors which strongly affect the hotel occupancy. However, it is difficult to consider these factors in the forecasting model by using a time series model or causal model. Therefore, a recurrent and decomposed neural network-based hotel occupancy forecasting model has been proposed to resolve such problems. To validate our proposed neural network model, experiments have been performed using the real world data from a hotel. Based on the experiment's results, the proposed neural network model outperforms not only the ARIMA approach, but also other possible neural network models. This study also includes an interesting discussion about the issues that should be considered in applying a neural network to the forecasting domain through various comparative experiments between the time series model and the neural network, and among various types of neural networks.",
author = "Choi, {Hyung Rim} and Wooju Kim and An, {Sung Youn}",
year = "1997",
month = "12",
day = "1",
language = "English",
volume = "3",
pages = "121--136",
journal = "New Review of Applied Expert Systems",
issn = "1474-5003",
publisher = "Taylor Graham Publishing",

}

Recurrent and decomposed neural network-based hotel occupancy forecasting. / Choi, Hyung Rim; Kim, Wooju; An, Sung Youn.

In: New Review of Applied Expert Systems and Emerging Technologies, Vol. 3, 01.12.1997, p. 121-136.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Recurrent and decomposed neural network-based hotel occupancy forecasting

AU - Choi, Hyung Rim

AU - Kim, Wooju

AU - An, Sung Youn

PY - 1997/12/1

Y1 - 1997/12/1

N2 - Occupancy forecasting is one of the most important decisions a hotel's management must make. If a more accurate form of forecasting is available, the hotel managers can increase their profits through the efficient management of rooms based on the forecasts. However, there are two major problems in applying the traditional time series model to hotel occupancy forecasting. One of the reasons is due to the upper and lower bounds which exist in the hotel occupancy data. The other is that there are many judgmental and exogenous factors which strongly affect the hotel occupancy. However, it is difficult to consider these factors in the forecasting model by using a time series model or causal model. Therefore, a recurrent and decomposed neural network-based hotel occupancy forecasting model has been proposed to resolve such problems. To validate our proposed neural network model, experiments have been performed using the real world data from a hotel. Based on the experiment's results, the proposed neural network model outperforms not only the ARIMA approach, but also other possible neural network models. This study also includes an interesting discussion about the issues that should be considered in applying a neural network to the forecasting domain through various comparative experiments between the time series model and the neural network, and among various types of neural networks.

AB - Occupancy forecasting is one of the most important decisions a hotel's management must make. If a more accurate form of forecasting is available, the hotel managers can increase their profits through the efficient management of rooms based on the forecasts. However, there are two major problems in applying the traditional time series model to hotel occupancy forecasting. One of the reasons is due to the upper and lower bounds which exist in the hotel occupancy data. The other is that there are many judgmental and exogenous factors which strongly affect the hotel occupancy. However, it is difficult to consider these factors in the forecasting model by using a time series model or causal model. Therefore, a recurrent and decomposed neural network-based hotel occupancy forecasting model has been proposed to resolve such problems. To validate our proposed neural network model, experiments have been performed using the real world data from a hotel. Based on the experiment's results, the proposed neural network model outperforms not only the ARIMA approach, but also other possible neural network models. This study also includes an interesting discussion about the issues that should be considered in applying a neural network to the forecasting domain through various comparative experiments between the time series model and the neural network, and among various types of neural networks.

UR - http://www.scopus.com/inward/record.url?scp=2742603537&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2742603537&partnerID=8YFLogxK

M3 - Article

VL - 3

SP - 121

EP - 136

JO - New Review of Applied Expert Systems

JF - New Review of Applied Expert Systems

SN - 1474-5003

ER -