Institutional Repository of Vilnius University
Giliųjų neuroninių tinklų, grafų ir klasikinių laiko eilučių metodų palyginimas akcijų kainoms prognozuoti /
Abstract
dc:descriptionApplications of graph theory for stock market time series forecasting. The author overviews and explains briefly the classic forecasting model ARIMA and compares it to deep learning networks such as LSTM, Stacked-LSTM and Transformers. The overview also includes non-traditional time series analysis with graph theory and Time2Vec layer enhancement. The thesis proposes two methods on how constructed graphs might enhance time series data and deliver better model performance. Particular research determining the best model and methods is done and performance comparison based on empirical data is provided.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Bratčikov, Pijus,
- Contributors dc:contributor
-
- Raudys, Aistis
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:ELABAETD107116832&prefLang=en_US