TY  - JOUR
T1  - Optimization of Artificial Neural Network for Stock Market
Price Prediction Using an Enhanced Firefly Algorithm
AU - Stephen Gbenga, Fashoto AU - Ahmed Oloduowo, Ameen AU - Clement, Ogeh AU - Abdullateef, Balogun AU - Petros, Mashwama 
JO  - Research Journal of Applied Sciences
VL  - 13
IS  - 9
SP  - 532
EP  - 543
PY  - 2018
DA  - 2001/08/19
SN  - 1815-932x
DO  - rjasci.2018.532.543
UR  - https://makhillpublications.co/view-article.php?doi=rjasci.2018.532.543
KW  - Artificial neural network
KW  -firefly
KW  -optimization
KW  -price prediction
KW  -stock market
KW  -model
AB  - The aim of this study is to develop a system that predicts the future closing price of daily stocks
based on historic data of the stocks. The Artificial Neural Network (ANN) was employed to learn the historic
data and make predictions for the next few days while the Firefly Algorithm (FA) was used to optimize the
weights of the network for accurate predictions. The daily historic dataset of stock prices for five companies
trading the New York Stock Exchange (NYSE) from 13-14-10-2005 was used for the experiment. This study
shows that the proposed model made 6.8% better predictions with less average errors when compared with the
predictions made with ANN trained with the Genetic Algorithm (GA). The introduction of the reduction scheme
employed reduces the randomization parameter of the fireflies in the algorithm and this significantly improves
the prediction accuracy of the proposed model.
ER  -