Particle swarm optimization LSTM based stock prediction model

Due to the high stochasticity and complexity of stock forecasting, the and forecasting ability of a single model is limited. In order to accurately analyze and predict the impact of stock price changes over time a PSO-LSTM stock forecasting model is put forward. The model is improved and optimized on the basis of LSTM model. Particle swarm optimization algorithm can optimize the key parameters of LSTM model and make stock prediction more accurate. It is therefore good at dealing with complex non-linear problems with long-term dependencies. Experiments were conducted to construct the PSO-LSTM model with Shenzhen Ping An stock data respectively, and the forecasting effects on the model were compared with other forecasting models to do an analysis. The results show that the PSO-LSTM stock price forecasting model not only improves the forecasting accuracy but also has general applicability.