Institutional Repository of Vilnius University
Turistų ir nakvynių skaičiaus Lietuvos apgyvendinimo įstaigose prognozavimas naudojant "Google Trends" duomenis /
Abstract
dc:descriptionInformation about the number of tourists and their behaviour in the future is a crucial tool in planning the development of the tourism sector and realizing its full potential, especially when talking about accommodation businesses. Studies show that including online search query popu‐ larity data, such as „Google Trends“, in forecasting models can increase their accuracy, however, the effectiveness of this methodology has not been researched in the context of Lithuania. The primary aim of this research is to examine whether the inclusion of „Google Trends“ data in models for forecasting the number of tourists and overnight stays in accommodation businesses in Lithuania can increase their accuracy. To achieve this objective, the accuracy of models with and without „Google Trends“ data was compared across different categories of accommodation businesses and by tourists’ countries of origin. Two forecasting models were tested during the study: a classical time series model SARIMAX and a machine learning model – support vector regression. The study found that the inclusion of „Google Trends“ data can significantly improve accuracy when forecasting the number of domestic tourists, but has limitations when dealing with foreign tourists and all travellers. Additionally, it was concluded that the SARIMAX model is superior in forecasting both the number of tourists and the number of overnight stays.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Jasiukėnaitė, Nora,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD239028577&prefLang=en_US