Claim Missing Document
Check
Articles

Found 13 Documents
Search

Implementasi Algoritma XGBoost dengan Walk Forward Validation untuk Prediksi Harga Emas Antam Hisyam, Mochammad; Fitri, Zahratul; Aidilof, Hafizh Al Kautsar
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 4 (2025): Agustus 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i4.8693

Abstract

Accurate gold price prediction is crucial in supporting financial and investment decision-making. This study aims to develop and optimize a daily gold price prediction model using the Extreme Gradient Boosting (XGBoost) algorithm based on historical price data and technical indicators. The model was constructed to predict two types of prices, namely "Close" and "Buyback" prices in IDR/gram. Optimization was carried out using Bayesian Optimization to obtain the best hyperparameter combinations. The model was evaluated using a Walk Forward Validation (WFV) approach with a 14-day sliding window and two main evaluation metrics: Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results show that the model provides excellent predictive performance, with an average RMSE of 15,431.92 and MAPE of 1.03% for Close price, and RMSE of 15,382.64 and MAPE of 1.15% for Buyback price. The prediction visualizations indicate that the model consistently follows the actual price trend. Feature importance analysis reveals that technical indicators such as RSI, EMA, and MACD significantly contribute to the model. The success of this study demonstrates that an optimized XGBoost model can serve as a reliable approach for gold price forecasting and opens opportunities for developing more advanced predictive models in future research.
Heart Disease Classification Based on Medical Record Data Using the Logistic Regression Method Iswari, Syahyana; Dinata, Rozzi Kesuma; Aidilof, Hafizh Al Kautsar
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 1 (2025): September 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i1.8867

Abstract

Heart disease remains one of the primary causes of mortality globally and poses a significant public health concern, including in Indonesia. Early identification of individuals at risk is essential for lowering death rates and enhancing the success of medical interventions. This research focuses on developing a classification model for heart disease using the Logistic Regression technique, utilizing data extracted from patient medical records. The dataset comprises 100 entries, each containing six key features: age, gender, blood pressure, heart rate, respiratory rate, and chest pain. The model was trained on 80% of the data and evaluated using the remaining 20%. Model performance was assessed using several metrics, including accuracy, precision, recall (sensitivity), F1-score, confusion matrix, and the ROC (Receiver Operating Characteristic) curve. The evaluation results revealed an accuracy of 95%, precision of 100%, recall of 88.89%, F1-score of 94.12%, and an AUC score of 0.99. These outcomes suggest that Logistic Regression is highly effective for classifying heart disease risk and can serve as a valuable tool in early detection systems supported by medical record data.
Pendampingan Implementasi dan Pelaksanaan E-office bagi Aparatur Gampong Cot Keumuneng Kabupaten Aceh Utara untuk Mendukung Smart governance Aidilof, Hafizh Al Kautsar; Rosnita, Lidya; Fitria, Rahma; Meiyanti, Rini; Yusdartono, Habib Muharry; Rangkuti, Haris Yunanda; Azwir, Andrea Micola
Jurnal SOLMA Vol. 15 No. 1 (2026)
Publisher : Universitas Muhammadiyah Prof. DR. Hamka (UHAMKA Press)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22236/solma.v15i1.16410

Abstract

Background: Perkembangan teknologi khususnya tekologi informasi telah merubah pola pelayanan masyarakat desa sebagai unit terkecil dari pemerintahan Republik Indonesia, dari yang sebelumnya terbatas pada ruang dan waktu, kini telah fleksibel dan lebih leluasa. Pengabdian kepada masyarakat ini dilakukan untuk mendukung program pemerintah menerapkan konsep smart village dimana dalam pelaksanaan administrasinya menerapkan smart government. Metode: Kegiatan pengabdian kepada masyarakat ini menyasar Aparatur Desa Cot Keumuneng yang berjumlah 15 orang sebagai peserta pelatihan yang nantinya akan menggunakan aplikasi e-office. Setelah pelatihan dan pendampingan dilakukan survey untuk melihat pemahaman aparatur desa dalam menggunakan e-office. Hasil: Kegiatan pengabdian kepada masyarakat ini mendapat hasil positif di kalangan aparatur desa dimana dengan adanya aplikasi ini proses persuratan di kalangan aparatur desa menjadi lebih efektif dan efisien. Dampak lainnya adalah pelayanan kepada masyarakat dapat lebih ditingkatkan karena fleksibilitas yang didapat dengan penerapan teknologi informasi. Kesimpulan: Kegiatan pengabdian kepada masyarakat ini sangat bermanfaat baik bagi internal aparatur desa maupun bagi pelayanan kepada warga desa sendiri dan aparatur desa berharap kegiatan serupa dapat terus dilaksanakan secara berkesinambungan.