APPLICATION OF ARTIFICIAL INTELLIGENCE ALGORITHMS IN MODELING ECONOMIC PROCESSES IN TOURISM
Keywords:
tourism economics, artificial intelligence, machine learning, demand forecasting, gradient boosting, neural network, modeling.Abstract
Tourism is one of the most dynamic sectors of the economy, but its key indicators — tourist flows, hotel occupancy, prices and revenues — depend on seasonality, prices, exchange rates and sudden external shocks. Traditional econometric models describe such processes only partly. This article examines the use of artificial intelligence (AI) algorithms for modeling economic processes in tourism. A five-stage framework is proposed: data collection, data preparation, AI modeling, model evaluation and decision support, with a feedback loop for regular retraining. The main tasks solved by AI in tourism are classified: demand forecasting, tourist segmentation, dynamic pricing and recommendation. A computational experiment on a synthetic monthly series of tourist arrivals with trend, seasonality and a crisis shock compares a seasonal naive method, linear regression, random forest, gradient boosting and a neural network. Gradient boosting gave the lowest forecast error (MAPE 4.3 %), while the regression model gave 6.6 % and the naive method 14.9 %. The results show that AI algorithms can improve the accuracy of planning in the tourism sector when combined with well-prepared data and correct evaluation.
References
1.Song H., Li G. Tourism demand modelling and forecasting — a review of recent research. Tourism Management. 2008;29(2):203–220.
2.Law R., Li G., Fong D.K.C., Han X. Tourism demand forecasting: a deep learning approach. Annals of Tourism Research. 2019;75:410–423.
3.Кобулова, М. А. (2024). Информационные технологии в медицинском образовании-как фактор повышения качества обучения. AndMI Xalqaro ilmiy-amaliy konferensiyalari, 1(1), 434-437.
4.Тешабоева, З. Т., & Кобулова, М. А. (2024). Совершенствование методов привлечения студентов к науке и исследованиям в ВУЗах. Science and innovation, 3(Special Issue 15), 442-444.
5.Кобулова Мохинабону Авазбековна (2024). ОСНОВНЫЕ НАПРАВЛЕНИЯ ИСПОЛЬЗОВАНИЯ КОМПЬЮТЕРНЫХ ТЕХНОЛОГИЙ В АДАПТИВНЫХ ОНЛАЙН ОБУЧАЮЩИХ СИСТЕМАХ. Universum: психология и образование, (10 (124)), 14-16
6.Hochreiter S., Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735–1780.
7.Breiman L. Random forests. Machine Learning. 2001;45(1):5–32.
8.Hyndman R.J., Athanasopoulos G. Forecasting: Principles and Practice. 3rd ed. Melbourne: OTexts; 2021.
9.Chen T., Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016:785–794.
10.Gretzel U., Sigala M., Xiang Z., Koo C. Smart tourism: foundations and developments. Electronic Markets. 2015;25(3):179–188.
11.Li X., Pan B., Law R., Huang X. Forecasting tourism demand with composite search index. Tourism Management. 2017;59:57–66.