Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal Sistem Informasi dan Informatika (SIMIKA) Jurnal Sistem Komputer dan Informatika (JSON)
Ahmad Rifai
Sriwijaya University
Computer Science & IT Control & Systems Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Perbandingan Performa Model Prediksi Volatilitas BTC/IDR Menggunakan LSTM dan ARIMA Fahren Affandi; Imam Akbar; Sella Juniastia Marsya Saputri; Zwesty Quatra; Allsela Meiriza; Ken Ditha Tania; Ahmad Rifai
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 4 (2026): Juni 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i4.9719

Abstract

Karakteristik fluktuatif pasar aset kripto yang ekstrem menuntut ketersediaan model peramalan yang andal sebagai penunjang strategi manajemen risiko investasi. Penelitian ini bertujuan untuk membandingkan pendekatan Long Short-Term Memory (LSTM) sebagai model deep learning sekuensial dan Autoregressive Integrated Moving Average (ARIMA) sebagai model statistik deret waktu dalam memprediksi log-volatility Bitcoin pada pasangan BTC/IDR periode 2018–2025. Dataset historis harian BTC/IDR diperoleh dari platform Binance dengan periode observasi Januari 2018 hingga Desember 2025, kemudian diproses melalui perhitungan log-return, estimasi realized volatility berbasis jendela 7 hari, transformasi logaritmik, serta normalisasi data. Evaluasi model menggunakan metode walk-forward validation dengan metrik Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa model LSTM memperoleh MAE sebesar 0,5126, RMSE sebesar 1,0408, dan R² sebesar 0,6803, sedangkan model ARIMA menghasilkan MAE sebesar 0,5430, RMSE sebesar 1,0217, dan R² sebesar 0,7052 pada konfigurasi terbaiknya. Meskipun LSTM memiliki MAE yang lebih rendah, model ARIMA menunjukkan performa yang lebih unggul berdasarkan nilai RMSE yang lebih kecil dan R² yang lebih tinggi, sehingga lebih efektif dalam menjelaskan variasi data serta menangkap fluktuasi ekstrem pada volatilitas Bitcoin. Secara keseluruhan, hasil penelitian menunjukkan bahwa model ARIMA lebih representatif dalam memodelkan dinamika log-volatility Bitcoin dibandingkan model LSTM. Temuan ini menegaskan bahwa pemilihan model prediksi volatilitas perlu mempertimbangkan karakteristik data yang dinamis dan fluktuatif. Penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan model prediksi volatilitas yang adaptif, khususnya pada pasar cryptocurrency di Indonesia.
ANALISIS SPASIO-TEMPORAL DETEKSI ANOMALI SUHU PERMUKAAN BUMI ISOLATION FOREST: STUDI KASUS INDONESIA Nicolaus Owen Marvell; Muhammad Iqbalul Khoiri; Chrisjuanito Clancy; Ken Ditha Tania; Allsela Meiriza; Ahmad Rifai
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 9 No. 2 (2026): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v9i2.4626

Abstract

Land surface temperature (LST) is an important indicator of climate change because increasing surface temperatures can trigger environmental degradation, drought, and extreme weather events. In Indonesia, long-term monitoring of extreme temperature anomalies remains limited, as most studies rely on conventional statistical methods that are less effective in detecting complex and non-linear anomaly patterns. Therefore, this study analyzes the spatio-temporal dynamics of LST and identifies extreme temperature anomalies across Indonesia during 1940–2024 using a machine learning approach. Monthly LST data were examined through exploratory data analysis (EDA), including temporal trend analysis and 10-year moving averages, to characterize long-term temperature variability, while the Isolation Forest algorithm was implemented as an unsupervised anomaly detection method using n_estimators = 100 and contamination = 0.05. The results identified 51 temperature anomalies, representing approximately 5% of the 1,020 monthly observations analyzed. Most anomalies occurred during periods associated with major climate disturbances and corresponded closely with documented El Niño events, particularly in 1997–1998 and 2015. Trend analysis revealed a persistent increase in Indonesia’s surface temperature, indicating an ongoing warming pattern consistent with climate change, while anomaly score distributions showed a clear separation between normal and extreme observations, confirming the effectiveness of the Isolation Forest algorithm. These findings demonstrate that integrating spatio-temporal analysis with machine learning provides a robust framework for detecting extreme temperature events and monitoring climate variability, thereby supporting climate risk assessment and strengthening BMKG’s early warning systems for climate change adaptation and mitigation.
KOMPARASI MODEL REGRESI DALAM MEMPREDIKSI GAJI PEKERJAAN ARTIFICIAL INTELLIGENCE M Rafly Ramdhani; M Luthfi Aldi Pratama; Muhammad Emirshah Yusuf; Ken Ditha Tania; Allsela Meiriza; Ahmad Rifai
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 9 No. 2 (2026): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v9i2.4627

Abstract

The increasing demand for Artificial Intelligence-related jobs has intensified global labor market dynamics, characterized by high salary variability and growing industry uncertainty. These conditions pose significant challenges for organizations and professionals in determining accurate, objective, and data-driven salary estimations. This study aims to develop and compare the performance of several regression models for predicting Artificial Intelligence job salaries, namely Linear Regression, Gradient Boosting, and Support Vector Regression. A large-scale global job postings dataset is employed, incorporating conventional job attributes such as location, experience level, and job type. In addition, this study integrates industry risk variables, including layoff risk and automation risk, to capture more realistic labor market dynamics. The research methodology consists of data preprocessing, model development using a machine learning pipeline to ensure consistent processing between training and testing data, and performance evaluation. The dataset is split into training and testing sets using an 80:20 ratio, and model performance is assessed using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the coefficient of determination (R²). The experimental results indicate that Gradient Boosting achieves the best performance with the lowest prediction errors and the highest explanatory power, followed by Linear Regression. In contrast, Support Vector Regression exhibits relatively poor performance on high-dimensional feature representations. These findings confirm that ensemble-based approaches are more effective in modeling the heterogeneous and non-linear salary structures of Artificial Intelligence jobs and provide valuable insights for data-driven labor market analysis.
Co-Authors Allsela Meiriza, Allsela Chrisjuanito Clancy Fahren Affandi Imam Akbar Ken Ditha Tania M Luthfi Aldi Pratama M Rafly Ramdhani Muhammad Emirshah Yusuf Muhammad Iqbalul Khoiri Nicolaus Owen Marvell Sella Juniastia Marsya Saputri Zwesty Quatra