Institutional Repository of Vilnius University
Mašininio mokymosi algoritmų taikymas prognozuojant akcijų kainų kryptį /
Abstract
dc:descriptionIn this work were investigated efficient market hypothesis problem, support vector machines and neural networks concept. Analyzed all forms of stock market efficiency and summarized earlier researches results of denying the efficient market hypothesis. This work tries to deny efficient market hypothesis by applying machine learning algorithms for classification task. Using support vector machines with kernel and neural networks was tried to reach highest stock price direction prediction accuracy. For that was used ”Alibaba” historical stock price data. While using stock price trends indicators from technical analysis for machine learning models training was received high accuracy of stock price direction prediction.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Micikevičius, Mantas,
- Contributors dc:contributor
-
- Šimėnas, Raivydas
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:ELABAETD107117463&prefLang=en_US