Резюме:

Predicting stock market returns is an important task in portfolio management. Successfully predicting the future price of a stock can yield significant returns. However, the abnormality of the financial market prevents simple models from predicting future asset prices with high accuracy. Current research in this area is focused on deep learning, which involves combining multiple artificial neurons as layers to create non-linear models that can learn to perform a diverse and complex task from a large number of examples. In this paper we will build a model based on recurrent neural networks, more precisely on the LSTM network for predicting future stock market prices.

Keywords: LSTM, long short-term memory, recurrent neural network, time series prediction

Mafutala G.Kh. ¹ Financial time series forecasting using recurrent neural networks LSTM // Современные информационные технологии. – 2025. – № 5;
URL: infotex.esrae.ru/7-70 (Date Access: 07.07.2026).

Today: 175 | Week: 175 | Total: 175

Comments (0)