Optimizing trading strategies in volatile markets with LSTM neural network approach

Purpose Accurate prediction of stock prices is of particular importance due to the wide-ranging effects it has on financial decisions. Design/methodology/approach In this study, long short-term memory (LSTM) neural networks have been used to model and predict future stock prices. These networks are suitable for this application due to their ability to identify complex temporal patterns and retain long-term information. Historical stock price data is used as input to the model for 2023–2024, and a model for price prediction is developed using LSTM neural networks. Findings The results indicate that the LSTM model can predict stock price trends with acceptable accuracy, but still faces challenges such as market fluctuations and sudden changes. Originality/value This research can serve as a supportive tool for financial analysts and investors to improve financial decision-making.