Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Informatika: Jurnal Pengembangan IT
Giovanka Steviano Harry Premono
Universitas Kristen Duta Wacana
Computer Science & IT

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

Found 1 Documents
Search

 1 
Implementasi Trading Strategy pada Saham Sektor Energi dengan Support Vector Machine dan Indikator Teknikal Giovanka Steviano Harry Premono; Nugroho Agus Haryono; Yuan Lukito
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10379

Abstract

The energy sector in the Indonesian capital market is characterized by high volatility, which is sensitive to external factors. This sensitivity leads to complexity in investment decision-making and trader emotional bias. This study employs a Support Vector Machine (SVM)-based trading strategy that incorporates technical indicators, such as Bollinger Bands, the Stochastic Oscillator, On-Balance Volume, and the Average Directional Index, to generate objective transaction signals for 14 energy sector stocks. Historical data from 2015 to 2025 was used, and three kernel types (RBF, polynomial, and sigmoid) were optimized through grid search. The evaluation used classification metrics and backtesting with an initial capital of Rp 100 million. The results showed F1 scores ranging from 35.83% to 47.86%. DEWA achieved the best performance with an accuracy of 66.67% and an F1 score of 47.86%. Backtesting yielded positive returns for 71.4% of stocks, with an average return of 26.85%. RAJA achieved optimal performance, with a 158.97% return and a Sharpe ratio of 1.48, outperforming the buy-and-hold strategy by 37.47%. The main advantage lies in superior risk management, with an average drawdown of -10.64%, compared to the buy-and-hold strategy -48.91%. This results in a 76.1% reduction in risk. The SVM strategy proved effective for low-risk tolerance investors but underperforms during periods of extreme bullish momentum.
Co-Authors Nugroho Agus Haryono Yuan Lukito