Stock Market Prediction Framework Based on the Fruit Fly Optimization Method

Abstract

Stock market prediction helps investors in decision-making process of investment to achieve profit. Recently, the deep learning method shows the significant performance in the stock market prediction. These deep learning models have the drawback of overfitting problems when it processing number of features. In this research, the fruit fly optimization method has been proposed for the feature reduction process in the stock market prediction. The fruit fly method has the advantages of simple computation processes and less number of parameter for tuning. The fruit fly method selects more relevant features to reduce the overfitting problem in the Long Short Term Memory (LSTM) classifiers. The Nifty 50 and S&P 500 data were applied to test the efficiency of the proposed model. The obtained result shows that the fruit fly method based framework achieved more efficiency than other techniques. The fruit fly based framework has 0.426 of Mean Square Error (MSE) and the existing firefly method has 0.621 MSE.