cover
Contact Name
Anna Islamiyati
Contact Email
jurnalestimasi@unhas.ac.id
Phone
-
Journal Mail Official
jurnalestimasi@unhas.ac.id
Editorial Address
Jl. Perintis Kemerdekaan Km. 10 Tamalanrea Makassar - Indonesia, 90245
Location
Kota makassar,
Sulawesi selatan
INDONESIA
ESTIMASI: Journal of Statistics and Its Application
Published by Universitas Hasanuddin
ISSN : 2721379X     EISSN : 27213803     DOI : http://dx.doi.org/10.20956/ejsa
Core Subject : Education,
ESTIMASI: Journal of Statistics and Its Application, is a journal published by the Department of Statistics, Faculty of Mathematics and Natural Sciences, Hasanuddin University. ESTIMASI is a peer – reviewed journal with the online submission system for the dissemination of statistics and its application. The material can be sourced from the results of research, theoretical, computational development and all fields of science development that are in one group.
Articles 107 Documents
Analisis Sentimen Terhadap Ulasan Aplikasi Mobile JKN Menggunakan Metode Machine Learning Logistic Regression, SVM, dan CSVM Fernando, Moch. Firman; Ahmad, Davin Anezta; Rachmanto, Nugroho Fajar; Wara, Shindi Shella May; Hindrayani, Kartika Maulida
ESTIMASI: Journal of Statistics and Its Application Vol. 6, No. 2, Juli, 2025 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v6i2.44943

Abstract

One of the digital-based public service innovations in the health sector is the Mobile JKN application developed by BPJS Kesehatan. This application allows people to get health services more easily, effectively, and integrated. The purpose of this study is to evaluate user perceptions of the Mobile JKN application through collecting reviews from the Google Play Store. The collected data was analyzed using TF-IDF text mining technique and Chi-Square feature selection. Furthermore, logistic regression, support vector machine (SVM), and clustered SVM (CSVM) algorithms were used to perform sentiment classification. Comments were categorized into three categories: positive, neutral, and negative. The evaluation results show that CSVM has an accuracy value of 93%, precision of 94%, recall of 84%, and F1 value of 89%. Although features such as online registration and digital cards received positive feedback, sentiment analysis showed that most reviews were negative, especially regarding technical issues. The results show that ML-based algorithms can be effectively used to assess how people perceive digital services. These results can be used as a basis for BPJS Kesehatan to improve and develop new services.
Implementasi Model Long Short Term Memory (LSTM) Pada Proyeksi Harga Saham (Studi Kasus: PT. Pertamina Geothermal Energy (Persero)) Arisona, Dian Christien; Agusrawati, Agusrawati; Makkulau, Makkulau; Yahya, Irma; Wibawa, Gusti Ngurah Adhi; Baharuddin, Baharuddin; Fahyuni, Putri Riski
ESTIMASI: Journal of Statistics and Its Application Vol. 6, No. 2, Juli, 2025 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v6i2.44963

Abstract

This research presents a comprehensive analysis of the Long Short Term Memory (LSTM) method in projecting the stock price of PT. Pertamina Geothermal Energy (Persero). Utilizing daily stock price data, the LSTM model achieves a high level of accuracy with a Mean Absolute Percentage Error (MAPE) value of 0.84%. The LSTM's gate mechanism (input, forget, output) enables it to store long-term information, controlling the flow of information to update memory, delete irrelevant data, and generate predictions. Optimized with backpropagation through time (BPTT) and activation functions, the LSTM model proves effective in investment decision making, providing valuable insights for investors and market players to anticipate stock price fluctuations. This research demonstrates the great potential of machine learning in financial analysis, particularly in stock price projection and time series analysis. The results indicate that LSTM can be a valuable tool for investors and financial analysts, enhancing their ability to make informed decisions.
Spatial Modeling of Earthquake Risk in Sulawesi and Maluku Based on Geological Factors Rahmawati, Syarifah Desy
ESTIMASI: Journal of Statistics and Its Application Vol. 6, No. 2, Juli, 2025 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v6i2.45160

Abstract

The convergence of the Eurasian, Indo-Australian, and Pacific tectonic plates in the Sulawesi and Maluku regions results in high seismic activity, making these areas prone to frequent earthquakes. This study aims to analyze the spatial distribution of earthquake events and assess the influence of geological features such as volcanoes, active faults, and subduction zones on earthquake risk. Using the inhomogeneous Thomas cluster process, spatial modeling was conducted based on earthquake epicenter data from 2009 to 2020 with magnitudes ≥ 4.5. Each epicenter's distance to the nearest geological feature was used as a covariate. The results of the Chi-square test indicate significant spatial inhomogeneity, while the inhomogeneous K-function reveals that earthquakes tend to occur in clustered patterns. Parameter estimates show that proximity to volcanoes has the most substantial impact, increasing earthquake intensity by approximately 1.8 times for every 100 km closer to a volcano. Faults and subduction zones contribute with relative effects of 0.7 and 0.9 times, respectively. The model demonstrates good fit based on envelope simulation. Earthquake risk prediction maps identify Gorontalo, North Sulawesi, Central Sulawesi, Maluku, and North Maluku as high-risk zones. This model can serve as a valuable tool to support disaster mitigation planning and improve regional earthquake preparedness strategies.
Pemetaan Indeks Khusus Penanganan Stunting (IKPS) Indonesia menggunakan Metric Multidimensional Scaling (MMDS) Purnama, Eka
ESTIMASI: Journal of Statistics and Its Application Vol. 6, No. 2, Juli, 2025 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v6i2.45235

Abstract

This study aims to map the Special Handling Index for Stunting (Indeks Khusus Penanganan Stunting/IKPS) in Indonesia using Metric Multidimensional Scaling (MMDS) to identify spatial patterns and similarities in characteristics among provinces. The MMDS analysis produced a visualization that grouped 34 provinces into 10 clusters with similar IKPS characteristics and spatial proximity within each group. Additionally, three provinces were identified as outliers due to their significantly greater spatial distances from other provinces, these provinces are DI Yogyakarta, Gorontalo, and Papua. Model quality evaluation showed a STRESS value of 0.0248 and a coefficient of determination (R²) of 0.9993, indicating an excellent fit in representing the spatial data, thus making the clustering model on the spatial map reliable for use. These findings provide a comprehensive overview of the distribution and characteristics of stunting handling in Indonesia. Therefore, the clustering results can serve as a strategic foundation for stakeholders and policymakers in designing strategies and implementing more focused and effective interventions to address and manage stunting across various regions in Indonesia.
Mendeteksi Unsur Depresi pada Unggahan Media Sosial Menggunakan Metode Machine Learning dengan Optimasi Berbasis Inspirasi Alam Santoso, Zein Rizky; Wigena, Aji Hamim; Kurnia, Anang
ESTIMASI: Journal of Statistics and Its Application Vol. 6, No. 2, Juli, 2025 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v6i2.45516

Abstract

Social media has now become an inseparable part of everyday life, including in expressing emotions and mental states. One popular platform is X (formerly Twitter), where many users indirectly share signs of depression. This study develops a classification model to detect indications of depression in social media posts, using machine learning algorithms and feature selection techniques based on nature-inspired algorithms. The classification algorithms used include Naïve Bayes, k-Nearest Neighbors (k-NN), Decision Tree, Random Forest, and XGBoost. Each algorithm is combined with feature selection techniques using Particle Swarm Optimization (PSO), Bat Algorithm (BA), and Flamingo Search Algorithm (FSA). The models are evaluated based on accuracy, precision, recall, F1-score, and the number of features used. The results show that the combination of the Random Forest method with FSA-based feature selection (RF-FSA) delivers the best performance, with an accuracy of 82.2%, balanced precision and recall, and efficient feature usage. Another strong alternative is XGBoost with FSA (XGB-FSA), although it requires more features and longer computational time. This study demonstrates that selecting the right feature selection algorithm, particularly FSA, can significantly improve both the accuracy and efficiency of depression text classification models. The resulting model is expected to serve as a useful tool for early detection of depression symptoms from social media posts, allowing for quicker and more targeted interventions.
Perbandingan Metode Seasonal ARIMA dan Extreme Learning Machine dalam Prediksi Produksi Padi di Sulawesi Selatan Jamal, Rini; Baso, Andi M Alfin; Andi Febriyanti; Sitti Sahriman; Siswanto, Siswanto; Yunita, Andi Isna; Angriany, A. Muthiah Nur; Rahim, Rahmiati; Fadil, Muhammad
ESTIMASI: Journal of Statistics and Its Application Vol. 6, No. 2, Juli, 2025 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v6i2.45821

Abstract

South Sulawesi is one of the provinces that significantly contributes to national rice production. Therefore, accurate forecasting of rice production is crucial for food security planning and agricultural policy-making. This study aims to compare the performance of the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Extreme Learning Machine (ELM) methods in predicting rice production in South Sulawesi. SARIMA is a statistical forecasting method effective for data with seasonal patterns, while ELM is a machine learning approach capable of handling complex relationships among variables with high computational speed. Rice production data from the Central Statistics Agency (Badan Pusat Statistik) were used to evaluate the accuracy of both methods. The evaluation was conducted using forecasting error metrics such as Mean Absolute Percentage Error (MAPE). The results show that the SARIMA(1,1,0)(1,1,0)12 model outperformed ELM in predicting rice production in South Sulawesi. This is indicated by a lower MAPE value of 19.937%, compared to 21.632% for the ELM method.
Pengelompokan Kemiskinan di Provinsi Sulawesi Selatan Tahun 2023 dengan Metode K-Means Clustering Wulandari, A. Elisha; Baso, Andi M. Alfin; Fajri, Belia Nurul; Kalondeng, Anisa; Islamiyati, Anna; Pannu, Abdullah; Fadil, Muhammad; Vallarino, Alfian Akbar; Rahman, Anugrah Nur Isnaeni
ESTIMASI: Journal of Statistics and Its Application Vol. 6, No. 2, Juli, 2025 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v6i2.45824

Abstract

Poverty remains a significant social and economic issue in South Sulawesi Province. This study aims to classify districts/cities in South Sulawesi based on poverty levels using the K-Means Clustering method. The data used were obtained from the Central Bureau of Statistics (BPS) for 2023, including indicators such as the percentage of poor population, education level, and employment sector. The Silhouette Index method was applied to determine the optimal number of clusters. The results indicate that South Sulawesi is divided into two clusters, representing high and low poverty levels. The scatter plot further reveals that cluster 1 is more varied, while cluster 2 is more concentrated. These findings can serve as a foundation for formulating more targeted policies to reduce poverty in South Sulawesi.

Page 11 of 11 | Total Record : 107