Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Tri Kurniawan Putra
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Rekomendasi Aksi Saham dengan Pendekatan Teknikal pada PT Telekomunikasi Indonesia Tbk (TLKM) menggunakan Algoritme Learning Vector Quantization (LVQ) 2.1 Tri Kurniawan Putra; Sigit Adinugroho; Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 11 (2021): November 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Stocks is a tool for buying or selling transactions in the capital market. In trading, the investor always wants profits that have low risk of failure. Therefore, an analysis is needed to get recommendations that support the stock. The results of the analysis will provide recommendations that can be used by investors to buy shares, wait, or sell their stock. Classification algorithm can used for analysis, one of them is Learning Vector Quantization. The technical approach factors that become parameters in this study consist of opening price, highest price, lowest price, closing price, volume, adj. closed, and the proportion of changes. In this study, the researcher used the Learning Vector Quantization (LVQ) 2.1 algorithm. The process starts with the initialization of data input. Then do the normalization process. Determine the winning network, update its weight and reduce the value of α, until it reaches a certain epoch or value. Tests was performed using several parameters to determine the effect of those parameters on accuracy. The best test was obtained by using training data as much as 175 training data, the value of learning rate is 0.1 and 1000 iteration produced an accuracy value of 63.64%.
Co-Authors Adinugroho, Sigit Randy Cahya Wihandika