Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Algoritma
Gabriel, Evander
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
Analisis indikator Bollinger Bands, Stochastics dan Relative-Strength Index Untuk Prediksi Pergerakan Gold Futures Berbasis Deep Learning Gabriel, Evander; Lukito, Yuan; Haryono, Nugroho
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2264

Abstract

Gold futures price predictions are challenging due to high volatility and its role as a safe-haven asset influenced by global political and economic conditions. The right trading strategy is needed to take advantage of price fluctuations, one of which is through technical, fundamental, sentiment, and machine learning analysis. This study analyzes the effectiveness of technical indicators Bollinger Bands (BB), Stochastic Oscillator (STOCH), and Relative Strength Index (RSI) in predicting Gold Futures prices using the Deep Learning Long Short-Term Memory (LSTM) model. The research data consists of ±40,000 Gold Futures prices from Yahoo Finance, which are divided into training, validation, and test data using the sliding window method (20% shift from 0%–60%). Model performance is evaluated through Return, Real, Trade, Win-rate, and Profit-factor using back testing in Metatrader 5 (100 leverage). The results show that the LSTM model with BB features (period 20, deviation 2) produced the highest average return of $100.48, a win rate of 32.53%, and a profit factor of 2.30. The second-best model used a combination of the three indicators with an average return of $98.033, a win rate of 30.96%, and a profit factor of 2.12.
Co-Authors Nugroho Haryono Yuan Lukito