Year: 2025
Type: article
Abstract: Predicting stock prices is highly challenging due to the volatile, nonlinear, and multifactorial nature of the financial markets. Various studies have approached stock price prediction using models like Convolutional Neural Networks (CNNs) ,and Artificial Neural Networks (ANNs). However, traditional approaches often struggle with capturing long-term temporal dependencies and are sensitive to market volatility. In our study, we developed a stock price prediction model using Long Short-Term Memory (LSTM) networks, which are well-suited for learning patterns from sequential data. The proposed LSTM-based model achieved a high prediction accuracy of up to 97.2% for certain stocks, significantly outperforming traditional machine learning methods.
Author: Ayush Kumar -
Institution: Galgotias University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4410927308