Stock Price Forecasting using N-Beats Deep Learning Architecture
B. Samuel Naik
Banaras Hindu University (BHU), Varanasi, Uttar Pradesh-221 005, India.
V C Karthik
The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi – 110 012, India.
B. Manjunatha
The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi – 110 012, India.
Veershetty
The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi – 110 012, India.
Harish Nayak, G. H.
University of Agricultural Sciences, Dharwad, Karnataka– 580 005, India.
B S Varshini
The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi – 110 012, India.
Halesha P
Banaras Hindu University (BHU), Varanasi, Uttar Pradesh-221 005, India.
S Govinda Rao *
Department of Statistics and Computer Applications, ANGRAU Agricultural College Naira, Srikakulam, Andhra Pradesh -522 101, India.
*Author to whom correspondence should be addressed.
Abstract
Stock prices present unique forecasting challenges due to factors such as market volatility, investor sentiment, and economic indicators, which contribute to significant fluctuations in time series data. This paper addresses these complexities by applying Deep Learning (DL) models to predict stock prices, with a particular focus on the S&P 500 index. Although DL models have shown remarkable success in fields like image processing and natural language processing, they require specialized architectures to effectively handle time series forecasting. This study examines the Neural Basis Expansion Analysis for Interpretable Time Series Forecasting (N-BEATS) model, a novel DL architecture specifically tailored for time series data, using S&P 500 stock price data. The performance of N-BEATS is benchmarked against three baseline models: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). The evaluation metrics include Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Results indicate that the N-BEATS model consistently surpasses the other models in all metrics. Additionally, the Diebold-Mariano (DM) test further validates the superior predictive accuracy of the N-BEATS model compared to the alternatives. This research underscores the potential of the N-BEATS model to significantly improve stock price forecasting, offering valuable insights for investors, financial analysts, and other market participants.
Keywords: Stock price, basis expansion, Convolutional Neural Network (CNN), deep learning, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), N-BEATS