Institutional Repository of Vilnius University
Giliųjų neuroninių tinklų taikymas kriptovaliutų kainų ir tendencijų prognozavimui /
Abstract
dc:descriptionThe cryptocurrency market has exploded in popularity over the past decade, attracting billions of dollars in investment. Cryptocurrency price forecasting has also become very relevant to predict future price movements and find profitable investment opportunities. The application of deep neural networks is one of the promising technologies in this field. Gated Multilayer Perceptron (GMLP) is one of these deep learning models, which has been initially used for image classification with excellent performance even without the use of a self-attention mechanism. The study showed that a gated multi-layer perceptron is able to predict „Bitcoin“ prices. While achieving higher errors than other deep neural models, this model can highlight the complex relationships between past price movements and future trends, providing investors with a prediction of future price movements.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Rancas, Arijus,
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:ELABAETD192847242&prefLang=en_US