Md-Pred: A Multidimensional Hybrid Prediction Model Based on Machine Learning for Hotel Booking Cancellation Prediction

被引:1
作者
Tian, Xinyuan [1 ]
Pan, Bingqin [2 ]
Bai, Liping [3 ]
Mo, Deyun [3 ,4 ]
机构
[1] Macau Univ Sci & Technol, Macau Inst Syst Engn, Macau 999078, Peoples R China
[2] Sichuan Digital Transportat Technol Co Ltd, Chengdu 610095, Sichuan, Peoples R China
[3] Macau Univ Sci & Technol, Fac Innovat Engn, Macau 999078, Peoples R China
[4] Lingnan Normal Univ, Sch Mech & Elect Engn, Zhanjiang 524000, Guangdong, Peoples R China
关键词
Machine learning; cancellation prediction; CatBoost; LGBM; SARIMAX; SARIMAX; DEMAND;
D O I
10.1142/S0218001423510096
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Hotel order cancellation prediction has always been an influential part of hotel management. A better prediction model can optimize the accuracy of the prediction and thus enhance the value of subsequent business analysis and operational optimization. In this paper, a multidimensional hybrid evaluation prediction model Md-Pred is proposed for the first time. It combines the CatBoost, LGBM classifier, and SARIMAX time series algorithm, which can more effectively balance the influence of various features on classification problems as well as differentiate between objective features and subjective features. Results indicate that the performance of the prototype is significant, a new level of accuracy in predicting hotel order cancellations and future guest flow has been achieved.
引用
收藏
页数:21
相关论文
共 21 条
  • [1] Abou Omar K. B., 2018, PREPRINT
  • [2] Customer churn prediction in telecom using machine learning in big data platform
    Ahmad, Abdelrahim Kasem
    Jafar, Assef
    Aljoumaa, Kadan
    [J]. JOURNAL OF BIG DATA, 2019, 6 (01)
  • [3] Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees
    Ahmad, Muhammad Waseem
    Reynolds, Jonathan
    Rezgui, Yacine
    [J]. JOURNAL OF CLEANER PRODUCTION, 2018, 203 : 810 - 821
  • [4] Modeling and Forecasting Daily Hotel Demand: A Comparison Based on SARIMAX, Neural Networks, and GARCH Models
    Ampountolas, Apostolos
    [J]. FORECASTING, 2021, 3 (03): : 580 - 595
  • [5] Hotel booking demand datasets
    Antonio, Nuno
    de Almeida, Ana
    Nunes, Luis
    [J]. DATA IN BRIEF, 2019, 22 : 41 - 49
  • [6] Overview and comparative study of dimensionality reduction techniques for high dimensional data
    Ayesha, Shaeela
    Hanif, Muhammad Kashif
    Talib, Ramzan
    [J]. INFORMATION FUSION, 2020, 59 : 44 - 58
  • [7] LGBM: a machine learning approach for Ethereum fraud detection
    Aziz R.M.
    Baluch M.F.
    Patel S.
    Ganie A.H.
    [J]. International Journal of Information Technology, 2022, 14 (7) : 3321 - 3331
  • [8] Evaluating a seasonal autoregressive moving average model with an exogenous variable for short-term timber price forecasting
    Banas, Jan
    Utnik-Banas, Katarzyna
    [J]. FOREST POLICY AND ECONOMICS, 2021, 131
  • [9] Modeling and forecasting hourly electricity demand by SARIMAX with interactions
    Elamin, Niematallah
    Fukushige, Mototsugu
    [J]. ENERGY, 2018, 165 : 257 - 268
  • [10] Panel-Data Estimation in Finance: Testable Assumptions and Parameter (In)Consistency
    Grieser, William D.
    Hadlock, Charles J.
    [J]. JOURNAL OF FINANCIAL AND QUANTITATIVE ANALYSIS, 2019, 54 (01) : 1 - 29