Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JSIKTI (Jurnal Sistem Informasi dan Komputer Terapan Indonesia)
Racmadhani, Budi
Unknown Affiliation
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Forecasting USD to IDR Exchange Rates Using Prophet Time-Series Model B, Muslimin; Afak, Richa Rachmawati; Racmadhani, Budi
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 4 (2024): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.237

Abstract

This study evaluates the effectiveness of the Prophet time-series model in forecasting USD to IDR exchange rates using a historical dataset of 2812 daily records, including opening and closing prices, highs, lows, and percentage changes. Data preprocessing steps, such as handling missing values and standardizing numeric fields, were performed to ensure data quality. Prophet, developed by Facebook, was chosen for its capability to model seasonality, irregular patterns, and external regressors, outperforming traditional models like ARIMA. The model's performance was validated using error metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE), demonstrating its predictive accuracy. Comparative analysis with ARIMA confirmed Prophet’s superior ability in capturing complex patterns in volatile financial data. The inclusion of external factors such as inflation rates and global economic indicators further improved the forecast accuracy. The results provide valuable insights for policymakers, investors, and financial analysts, supporting more informed decision-making and risk management strategies. This research highlights the importance of proper data preprocessing and advanced forecasting techniques for improving currency prediction accuracy, especially in emerging markets like Indonesia. Future research could explore hybrid models combining Prophet with machine learning techniques for enhanced forecasting capabilities.
Hypertension Risk Prediction Using GRU-Based Neural Network with Adam Optimization B, Muslimin; Racmadhani, Budi; Rudito, Rudito
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 2 (2023): December
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.258

Abstract

Hypertension remains one of the most prevalent chronic conditions worldwide and continues to be a major contributor to cardiovascular morbidity and mortality. Early identification of individuals at high risk is essential, yet conventional screening approaches often rely on periodic clinical examinations that may overlook subtle lifestyle or behavioral indicators. This study aims to address this challenge by developing a predictive model that estimates hypertension risk using a GRU-based neural network enhanced with the Adam optimization algorithm. The motivation for using this approach stems from the ability of GRU networks to capture nonlinear feature interactions and the effectiveness of Adam in improving training stability and convergence. The proposed system incorporates a structured preprocessing pipeline, feature scaling, and a sequential model architecture to classify individuals into hypertension and non-hypertension groups. The results show that the model achieves strong predictive performance, supported by accuracy trends, loss reduction patterns, and confusion matrix analysis that collectively demonstrate consistent learning behavior. The evaluation indicates that the GRU classifier successfully recognizes relevant health attributes such as stress levels, salt intake, age, sleep duration, and heart rate. Future research may explore expanded datasets, additional health indicators, or hybrid architectures to further enhance accuracy and improve clinical applicability. Overall, this work contributes an interpretable and efficient approach for health risk prediction and supports the development of intelligent digital health monitoring systems.
Co-Authors Afak, Richa Rachmawati Muslimin B, Muslimin Rudito Rudito