TY - GEN
T1 - Forecasting average room rate using k-nearest neighbor at Hotel S
AU - Asy'ari, Vaizal
AU - Anshori, Mohamad Yusak
AU - Herlambang, Teguh
AU - Farid, Imam Wahyudi
AU - Fidita Karya, Denis
AU - Adinugroho, Mukhtar
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In managing a hospitality business, it takes a lot of data and analysis to make the right decisions. One important indicator in assessing the performance of a hotel is the Average Room Rate (ARR) which shows the average price of rooms sold by the hotel in a certain period. From the ARR data obtained, it can make a picture of the future regarding expansion to increase the value of ARR in the future. In this study, ARR forecasting was carried out for Hotel S using the k-nearest neighbor (k-NN) method. The dataset used in this study is in the form of room sold out, room revenue, and average room rate at Hotel S from April 2018 to June 2023. The simulation was carried out by dividing the data into training data and testing data with a ratio of 70:30 and 80:20, and the selection of k-values are 3 to 7. The forecasting results that have been carried out using k-NN for split data 70%:30% produce an optimal RMSE of 6,335 at k-values is 3. The forecasting results that have been carried out using k-NN for 80%:20% data split produce an optimal RMSE of 7,452 at k-values is 5. From this comparison, the results of forecasting ARR using k-NN obtained the best RMSE of 6,335. The results of this study can be used by Hotel S in determining the price of various types of rooms that are appropriate and expected to provide benefits for management.
AB - In managing a hospitality business, it takes a lot of data and analysis to make the right decisions. One important indicator in assessing the performance of a hotel is the Average Room Rate (ARR) which shows the average price of rooms sold by the hotel in a certain period. From the ARR data obtained, it can make a picture of the future regarding expansion to increase the value of ARR in the future. In this study, ARR forecasting was carried out for Hotel S using the k-nearest neighbor (k-NN) method. The dataset used in this study is in the form of room sold out, room revenue, and average room rate at Hotel S from April 2018 to June 2023. The simulation was carried out by dividing the data into training data and testing data with a ratio of 70:30 and 80:20, and the selection of k-values are 3 to 7. The forecasting results that have been carried out using k-NN for split data 70%:30% produce an optimal RMSE of 6,335 at k-values is 3. The forecasting results that have been carried out using k-NN for 80%:20% data split produce an optimal RMSE of 7,452 at k-values is 5. From this comparison, the results of forecasting ARR using k-NN obtained the best RMSE of 6,335. The results of this study can be used by Hotel S in determining the price of various types of rooms that are appropriate and expected to provide benefits for management.
KW - average room rate
KW - forecasting
KW - hotel
KW - k-nearest neighbor
UR - http://www.scopus.com/inward/record.url?scp=85186514778&partnerID=8YFLogxK
U2 - 10.1109/ICAMIMIA60881.2023.10427942
DO - 10.1109/ICAMIMIA60881.2023.10427942
M3 - Conference contribution
AN - SCOPUS:85186514778
T3 - 2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023 - Proceedings
SP - 496
EP - 500
BT - 2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023
Y2 - 14 November 2023 through 15 November 2023
ER -
