호텔 수요 예측을 위한 NSGA3 특징 선택 기반의 시간 컨볼루션 네트워크 모델
A Temporal Convolutional Network for Hotel Demand Prediction Based on NSGA3 Feature Selection
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
수요 예측은 관광 산업에서 수익 관리의 중요한 요소이다. 2010년대 이후 관광 산업의 세계화와 SNS와 같은 다양한 형태의 마케팅 및 정보 공유가 증가함에 따라 비선형 활동과 비정형 정보로 인해 예측이 어려워졌다. 이러한 문제를 해결하기 위한 다양한 예측 모델이 연구되었으며, 기계 학습(ML) 모델이 효과적으로 사용되었다. 본 연구에서는 특징 선택 기법(NSGA3)을 시계열 모델에 적용하고 성능을 비교하였다. 호텔 수요 예측에서 TCN 모델은 MAPE 9.73%로, 특징 선택을적용하지 않았을 때보다 7.05% 성능이 향상된 높은 예측 성능을 보였다. 본 연구 결과는 향상된예측 성능을 통해 의사결정 지원에 유용할 것으로 기대된다.
Abstract
Demand forecasting is a critical element of revenue management in the tourism industry. Since the 2010s, with the globalization of the tourism industry and the increase of different forms of marketing and information sharing, such as SNS, forecasting has become difficult due to non-linear activities and unstructured information. Various forecasting models for resolving the problems have been studied, and ML models have been used effectively. In this study, we applied the feature selection technique (NSGA3) to time series models and compared their performance. In hotel demand forecasting, it was found that the TCN model has a high forecasting performance of MAPE 9.73% with a performance improvement of 7.05% compared to no feature selection. The results of this study are expected to be useful for decision support through improved forecasting performance.
참고문헌 (27)
- K. Park, "A Time Series Forecasting Model with the Option to Choose between Global and Clustered Local Models for Hotel Demand Forecasting", The Korean Journal of BigData, 9(1), pp.31~47 (2024)[DOI]
- J. A. Rusman, "Crude Oil Price Forecasting : A Comparative Analysis of ARIMA, GRU, and LSTM Models", IEEE 9th International Conference on Computing, Engineering, and Design (ICCED) (2023)
- N. Dowlut, "Forecasting resort hotel tourism demand using deep learning techniques – A systematic literature review", Heliyon, 9(7), pp.e18385~ (2023)[DOI]
- J. Kim, "Demand Prediction of Furniture Component Order Using Deep Learning Techniques", The Korean Journal of BigData, 5(2), pp.111~120 (2020)[DOI]
- H. Ahn, "Optimization of Multiclass Support Vector Machine Using Genetic Algorithm : Application to the Prediction of Corporate Credit Rating", Journal of MIS Research, 16(3), pp.161~177 (2014)[DOI]
- Y. Pethe, "Feature Selection Using Genetic Algorithm for Software Fault Prediction", 2024 3rd International Conference on Applied Artificial Intelligence and Computing(ICAAIC), pp.1132~1137 (2024)
- A. Alghamdi, "A Hybrid Method for Big Data Analysis Using Fuzzy Clustering, Feature Selection and Adaptive Neuro-Fuzzy Inference System Techniques : Case of Mecca and Medina Hotels in Saudi Arabia", Arabian Journal for Science & Engineering, 48(2), pp.1693~1714 (2023)[DOI]
- X. Li, "Efficient Time Series Predicting with Feature Selection and Temporal Convolutional Network", 2021IEEE 4th International Conference on Computer and Communication Engineering Technology(CCET), pp.141~145 (2021)
- W. Zha, "An Aero-Engine Remaining Useful Life Prediction Model Based on Feature Selection and the Improved TCN", Franklin Open, 6 (2024)[DOI]
- P. Lara-Benítez, "Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting", Applied Sciences, 10(7), pp.2322~ (2020)[DOI]
- R. Wan, "Multivariate Temporal Convolutional Network : A Deep Neural Networks Approach for Multivariate Time Series Forecasting", Electronics, 8(8), pp.876~ (2019)[DOI]
- G. Selva Jeba, "River Flood Prediction through Flow Level Modeling Using Multi-Attention Encoder-Decoder-Based TCN with Filter-Wrapper Feature Selection", Earth Science Informatics, pp.1~17 (2023)[DOI]
- M. Liu, "Short-Term Load Forecasting Using EMD with Feature Selection and TCN-Based Deep Learning Model", Energies, 15(19), pp.7170~ (2022)[DOI]
- Y. LeCun, "Backpropagation Applied to Handwritten Zip Code Recognition", Neural Computation, 1(4), pp.541~551 (1989)[DOI]
- S. Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997)[DOI]
- J. Long, "Fully Convolutional Networks for Semantic Segmentation", 2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.3431~3440 (2015)
- R. Urraca, "Lecture Notes in Computer Science, vol. 9121" (2015)
- A. M. Usman, "Filter-Based Multi-Objective Feature Selection Using NSGA III and Cuckoo Optimization Algorithm", IEEE Access, 8, pp.76333~76356 (2020)[DOI]
- Y. Xue, "Multi-Objective Feature Selection with Missing Data in Classification", IEEE Transactions on Emerging Topics in Computational Intelligence, 6(2), pp.355~364 (2022)[DOI]
- A. Papasani, "Adaptive Neighborhood Adjustment Strategy Based on MOHHO and NSGA-III Algorithms for Feature Selection", IAENG International Journal of Applied Mathematics, 54(5), pp.917~935 (2024)
- M. S. Almutairi, "Selecting Features That Influence Vehicle Collisions in the Internet of Vehicles Based on a Multi-Objective Hybrid Bi-Directional NSGA-III", Applied Sciences, 13(4), pp.2064~ (2023)[DOI]
- Md Z. Alom, "A State-of-the-Art Survey on Deep Learning Theory and Architectures", Electronics, 8(3), pp.292~ (2019)[DOI]
- F. Karim, "Multivariate LSTM-FCNs for Time Series Classification", Neural Networks, 116, pp.237~245 (2019)[DOI]
- A. Ayodeji, "Causal Augmented ConvNet : A Temporal Memory Dilated Convolution Model for Long-Sequence Time Series Prediction", ISA Transactions, 123, pp.200~217 (2022)[DOI]