Arifa, Panji Lokajaya
Unknown Affiliation

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

Found 2 Documents
Search

PERBANDINGAN K-MEANS DAN K-MEDOIDS DALAM PENGELOMPOKKAN KOMODITAS EKSPOR INDUSTRI DI INDONESIA Arifa, Panji Lokajaya; Rahmasari, Hazelita Dwi; Aimandiga, Carlya Agmis; Fitrianto, Anwar; Yudhianto, Rachmat Bintang
MUST: Journal of Mathematics Education, Science and Technology Vol 10 No 2 (2025): DECEMBER
Publisher : Universitas Muhammadiyah Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30651/must.v10i2.28661

Abstract

International trade plays a crucial role in Indonesia's economic growth, particularly through industrial commodity exports. However, its heavy dependence on a few key commodities makes it vulnerable to global market fluctuations. This study aims to explore trends in industrial commodity export values ​​and compare the performance of cluster methods in grouping commodities based on their value patterns. The research data used are monthly export values ​​from 2022 to mid-2025, sourced from the Central Statistics Agency (BPS). The analytical methods used include trend exploration and cluster analysis with K-Means and K-Medoids using Dynamic Time Warping (DTW) distance. The results of the export value trend exploration indicate that palm oil dominates industrial export value, while other commodities tend to have stable patterns at medium to low values. Evaluation of clustering results using K-Means and K-Medoids each obtained 3 clusters indicating that K-Medoids provided the best performance by obtaining a Silhouette Score of 0.1577 and a Davies-Bouldin Index (DBI) of 1.7990. This value is better than K-Means which obtained a Silhouette Score of 0.1493 and a DBI of 2.3037 indicating that the method is less than optimal in separating clusters. This finding explains that K-Medoids is more robust against outliers and is able to provide more representative groupings. So it can provide a deeper understanding of commodity grouping patterns and contribute to providing export policy recommendations to reduce dependence on primary commodities and increase the export competitiveness of Indonesian industrial products.
OPTIMASI XGBOOST DALAM PREDIKSI KECEPATAN KENDARAAN SECARA REAL-TIME : PERBANDINGAN METODE TUNING HYPERPARAMETER Arifa, Panji Lokajaya; Sadik, Kusman; Soleh, Agus M; Suhaeni, Cici
Jurnal Gaussian Vol 15, No 1 (2026): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.15.1.01-11

Abstract

Real-time vehicle speed prediction plays a vital role in the development of intelligent transportation systems aimed at improving traffic flow and safety. This study investigates the performance of the XGBoost algorithm enhanced with three hyperparameter tuning techniques: Grid Search, Bayesian Optimization, and Genetic Algorithm. A simulated dataset was constructed reflect diverse urban traffic scenarios, incorporating environmental variables such as weather, road conditions, and traffic density. The models were assessed using 5 and 10-fold cross-validation based on prediction metrics (MSE, RMSE, MAE and R²) as well as computational efficiency in terms of training and inference time. The findings reveal that Bayesian Optimization achieves the highest prediction accuracy, while Grid Search offers the fastest training time. Genetic Algorithm demonstrates a balanced trade-off between accuracy and computational efficiency, making it a competitive and practical choice. These results highlight the importance of selecting hyperparameter tuning strategies based on specific system needs in real-time traffic prediction using XGBoost.