Back to search

Institutional Repository of Vilnius University

Gilūs neuroniniai tinklai finansinių vienetų kainų laiko eilutėms prognozuoti /

Abstract

dc:description

Financial unit price forecasting is one of the most complex activities in the finance field, it requires not only economic or political knowledge but as well a very in-depth market analysis. The financial community has long been trying to solve the problem of price forecasting. This paper presents a solution to this problem - forecasting financial unit price time series based on deep neural network models. In this work is performed an analysis of the literature, delving into different methods of price forecasting. An overview of the application of neural networks is performed as well as analyzed neural network models of different architectures such as RNN, CNN, TNN and stacked. Data from different financial units are collected and analyzed. Studies with neural network models of the above architectures are performed to evaluate the accuracy of the models. Later, the results of the models and the comparative model obtained in the study are qualitatively compared and the best neural network model for forecasting the prices of financial units is selected. Practical research has shown that neural network models of the RNN architecture best predicts the time series of financial unit prices compared to other architecture models examined in the work.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kriščiūnas, Vainius,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Kriščiūnas, Vainius,. Gilūs neuroniniai tinklai finansinių vienetų kainų laiko eilutėms prognozuoti /. Institutional Repository of Vilnius University, 2022. https://repository.vu.lt/VU:ELABAETD146241445&prefLang=en_US