Predicting stock market trends using neural network architectures, NVIDIA study case
View/
Keywords
Neural network architectures ; Stock market trends ; Neural network ; NVIDIA ; Recurrent Neural Networks (RNN) ; Long Short-Term Memory (LSTM) ; Stock price forecasting ; Machine learning ; Financial data analysis ; Stock price forecastingAbstract
This thesis presents the use of neural networks in stock market price prediction, addressing the limitations of traditional statistical and econometric models, and by focusing on feedforward neural networks, recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, their effectiveness in forecasting stock prices is analyzed, while at the same time, a literature review highlights their advantages and challenges, including data quality and model interpretability.
In the experimental section, a neural network system is trained and tested on historical stock market data to assess its predictive performance, with the findings indicating that neural networks significantly enhance prediction accuracy by capturing complex, nonlinear relationships, ighlighting the contribution of this thesis to the application of advanced machine learning techniques in finance, while at the same time, it provides valuable insights for improving financial decision-making processes in the future.
Postgraduate Studies Programme
Προηγμένα Συστήματα ΠληροφορικήςDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών ΣυστημάτωνNumber of pages
67Language
EnglishCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Όχι Παράγωγα Έργα 3.0 Ελλάδα