Institutional Repository of Vilnius University
Dirbtinis intelektas ir finansų potencialas /
Abstract
dc:descriptionThe main purpose of this thesis is to evaluate the potential of artificial intelligence technologies in the financial sector through a comprehensive literature review and an empirical study analysing the relationship between investor sentiment indicators and stock market dynamics. The thesis consists of four main parts: theoretical literature analysis, challenges of AI integration, empirical sentiment analysis, and future perspectives. The theoretical section explores the development of AI, its core technologies, and application opportunities in the financial sector. Special focus is placed on the impact of AI on automation, risk management, customer service, and the growing challenges related to energy efficiency and ethical considerations. The empirical part examines the relationship between sentiment indicators and two major ETF’s indices: S&P 500 (U.S.) and STOXX 600 (Europe). The study reveals that emotional investor sentiment, especially bearish sentiment has a statistically significant influence on stock price movements (p < 0.001), while structural sentiment indices show no significant short-term predictive power. The analysis applies correlation, regression, and visual time-series methods. The key findings indicate that successful AI implementation in finance depends on selecting relevant and timely data sources. Sentiment analysis demonstrates strong potential for short-term forecasting and risk evaluation. Additionally, energy efficiency strategies have become essential in sustainable AI system development. This thesis is relevant for both academic research and financial professionals aiming to integrate AI technologies more effectively.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Keblaitis, Augustas,
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:ELABAETD239012768&prefLang=en_US