Stock Market Prediction Framework Based on the Fruit Fly Optimization Method

,Parag Rastogi

doi:10.35940/ijeat.d7590.049420

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.

Highlights

Stock market forecasting is an interesting topic in financial time series analysis and has attracted many researchers
Neural Network has been used for non-linear analysis in many areas such as financial securities, Signal Processing and Pattern Recognition. This method has been widely used in many applications like stock market forecasting, document classification and so on due to its advantages [2]. Many optimization methods such as Genetic Algorithm (GA), Firefly Algorithm (FA), and others have been used in feature selection with Artificial Neural Network (ANN) to increases efficiency of stock market forecasting [3]
The fruit fly method has been proposed for the feature reduction process in the stock market forecasting and Long Short Term Memory (LSTM) classifier is used for the prediction

Summary

Introduction

Stock market forecasting is an interesting topic in financial time series analysis and has attracted many researchers. Neural Network has been used for non-linear analysis in many areas such as financial securities, Signal Processing and Pattern Recognition. This method has been widely used in many applications like stock market forecasting, document classification and so on due to its advantages [2]. Many optimization methods such as Genetic Algorithm (GA), Firefly Algorithm (FA), and others have been used in feature selection with Artificial Neural Network (ANN) to increases efficiency of stock market forecasting [3]. Stock market forecasting is complex and non-linear in nature, with complexity is created by the correlation of market behavior and investment psychology.

Methods

Results

Conclusion