No Detail Found!

Comparison artificial neural network methods of backpropagation and learning vector quantization for forecasting stock prices

Author(s)
SILVIA FIFI WARDHANI Information Systems Management Department, BINUS Graduate Program - Master of Information Systems Management, Bina Nusantara University, Jakarta, Indonesia
DIYURMAN GEA Information Systems Management Department, BINUS Graduate Program - Master of Information Systems Management, Bina Nusantara University, Jakarta, Indonesia
Abstract
During the COVID-19 pandemic stock trading is a hot topic of discussion and encourages new investors which positive impact on the market modal. Shares of PT. XL Axiata, Tbk. (EXCL) was sluggish despite reporting a surge profit in 2021, this prompted research on how to predict the stock price of EXCL for attract investors and encourage company to be more active in carrying out business strategies. In recent years, Artificial Neural Networks (ANN) are quite used in macroeconomics forecasting, because of their ability to detect and relate linear and non-linear functions. In this study, two ANN methods were used to predict the stock price of EXCL with backpropagation (BP) and Learning Vector Quantization (LVQ). In the prediction results, model evaluation is needed to measure the forecasting model from both methods, resulting in the confusion matrix with the accuracy, sensitivity, and specificity are provided. This research is given some value to stock action suggestions at EXCL.
Publication Details
Page(s) 6674-6685
DOI DOI not available
Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 100, Issue: 21, Year: 2022

Request the full text from PASTIC

Keywords
Confusion Matrix, Artificial Neural Networks (ANN), Backpropagation (BP), Stock Price EXCL, Learning Vector Quantization (LVQ)
0

Citations

0

Downloads

39

Views