Open AccessPrediction of Stock Market Index Using a Hybrid Technique of Artificial Neural Networks and Particle Swarm Optimization
Author(s) -
Farnaz Ghashami,
Kamyar Kamyar,
S. Ali Riazi
Publication year - 2021
Publication title -
applied economics and finance
Language(s) - English
Resource type - Journals
eISSN - 2332-7308
pISSN - 2332-7294
DOI - 10.11114/aef.v8i3.5195
Subject(s) - particle swarm optimization , artificial neural network , stock market , index (typography) , stock market index , computer science , data set , econometrics , data mining , artificial intelligence , mathematics , machine learning , geography , context (archaeology) , archaeology , world wide web
In this paper we examine the ability of Artificial Neural Network methods (ANN) for predicting the stock market index. We first conduct an ANN analysis and then optimize the ANN model using Particle Swarm Optimization algorithm (PSO) to improve the prediction accuracy. In terms of data, we use NASDAQ index which is one of the most widely followed indices in the United States. Empirical results show that by determining the optimal set of biases and weights using PSO, we can augment the accuracy of the ANN model for this stock market data set.