Institutional Repository of Vilnius University
Statistinių ir mašininio mokymosi metodų taikymas eksporto duomenų prognozavimui /
Abstract
dc:descriptionExport data forecasting is essential step regarding efficient product warehousing and logistics management. Main purpose of this paper is to apply statistical and machine learning methods for export demand forecasting. During this paper there were identified most popular methods in four different categories: regarding statistical metods – SARIMA, machine learning – SVR, deep learning – LSTM and hybrid – SARIMA-SVR. Additionally it was tried to improve the forecasting accuracy of the models used by adding additional statistical and exogenous features, augmenting the dataset size and searching for optimal model hyperparameters. Lastly, web-based forecasting system prototype was created that is capable of forecasting export data.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kasperavičius, Tomas,
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:ELABAETD210647041&prefLang=en_US