Prediction of stock closing price based on PSO-BP neural network

The stock trend is influenced by many factors, such as macroeconomic environment and policies. It is helpful for investors to improve the accuracy of trading by analyzing and predicting the stock trend with machine learning. We build a standard BP neural network model, and predict the closing price of SSEX Index according to the highest price, lowest price and volume. In addition, we also use genetic algorithm and particle swarm optimization to optimize the BP neural network model. The results show that the accuracy of the three models in predicting the stock trend of SSEX Index has reached more than $90 \%$. Both genetic algorithm and particle swarm optimization algorithm have improved the prediction accuracy of the models, but PSO-BP algorithm has better prediction results.