ESROP – KMUTT – Hybrid LSTM-GRU Architecture with Adaptive Attention for Financial Data
This research project focuses on using advanced machine learning techniques to better predict stock prices, specifically targeting stocks from the S&P 500. By combining powerful deep learning methods—such as LSTM and GRU networks—with adaptive attention mechanisms inspired by Transformer models, the project aims to create forecasting systems that can dynamically adapt to changing market conditions, like sudden increases in volatility or shifts between bull and bear markets. Currently, traditional models struggle when markets behave unpredictably, leading to less accurate forecasts. The new approach developed through this project could improve forecasting accuracy, helping financial institutions and researchers manage risk and make better-informed investment decisions. For both participating institutions—KMUTT and the University of Toronto — this collaboration will enhance their expertise in quantitative finance, encourage further research, and support the adoption of innovative AI-driven financial modeling techniques.
Voir la description complète du projetArthur Chan
King Mongkut’s University of Technology Thonburi
Mathematics
Finance and Insurance; Artificial Intelligence; Other
University of Toronto
Globalink Research Award
