Research on stock price prediction based on LSTM-Transformer fusion model in financial management
Bibliographic entry
Ailila, Kadierbieke. Research on stock price prediction based on LSTM-Transformer fusion model in financial management / Kadierbieke. Ailila, M. A. Sednina ; науч. рук. // XII Международная научно-техническая конференция, посвященная 25-летию Международного института дистанционного образования «Информационные технологии в образовании, науке и производстве» : Минск, 19-20 ноября 2025 г. / сост.: М. А. Седнина, М. Г. Карасёва, Д. О. Савчук. – Минск : БНТУ, 2026. – С. 78-85.
Abstract
Stock price prediction is a challenging task due to its non-linearity, volatility and temporal dependence that traditional models are hard to fully capture. This study proposes an LSTM-Transformer fusion model, combining LSTM’s strength in long-term temporal feature extraction and Transformer’s advantage in global correlation capture. Comparative experiments on multi-source financial data show the model outper-forms single deep learning and traditional models, providing reliable support for investment decision-making.