Stock Price forecasting based on Quantum Particle swarm optimization

The stock market is very volatile, so the change of the stock price is also widely concerned by investors. In this paper, a new stock price forecasting model based on Quantum Particle Swarm Optimization(QPSO) , Quantum Bee Colony Optimization Algorithm(QABC) and Quantum Fruit Fly Optimization Algorithm (QFOA) is proposed. The three methods all use BP neural network to adjust the parameters of particle swarm, bee colony and Drosophila to reach the optimal parameters. Taking the daily closing price of CITIC Securities and Tianfeng Securities, a large-scale and a small-scale securities company, as the object of empirical analysis, comparing the accuracy of the three methods in predicting stocks, it also analyzes whether the size of the company has an effect on the accuracy of the model. The results show that the prediction effect of qpso is the best, and the size of the company has some influence on the prediction effect.

Evaluation of Weight Decay Regularization Techniques for Stock Price Prediction using Gated Recurrent Unit Network

Stock price forecasting in the field of interest for many stock investors to earn more profit from stock trading. Nowadays, machine learning researchers are also involved in this research field so that fast, accurate and automatic stock price forecasting can be achieved. This research paper evaluated GRU network’s performance with weight decay reg-ularization techniques for predicting price of stocks listed NEPSE. Three weight decay regularization technique analyzed in this research work were (1) L1 regularization (2) L2 regularization and (3) L1_L2 regularization. In this research work, six randomly selected stocks from NEPSE were experimented. From the experimental results, we observed that L2 regularization could outperform L1 and L1_L2 reg-ularization techniques for all six stocks. The average MSE obtained with L2 regularization was 4.12% to 33.52% lower than the average MSE obtained with L1 regularization, and it was 10.92% to 37.1% lower than the average MSE obtained with L1_L2 regularization. Thus, we concluded that the L2 regularization is best choice among weight regularization for stock price prediction.