Jurnal Ilmiah Media Sisfo

Analisis dan prediksi Harga Saham menggunakan Metode Random Forest

Muhammad Hasbi — 2026-04-30

Stock price movements are highly volatile and influenced by various factors, making the investment decision-making process challenging, particularly for investors who rely on historical data. This study aims to analyze the performance of the Random Forest method in predicting the stock price of PT Bank Central Asia Tbk (BBCA) based on technical indicators. The methodology involves processing historical stock price data using a time-series approach, calculating technical indicators such as Exponential Moving Average, Moving Average, Relative Strength Index, Moving Average Convergence Divergence, and trading volume, as well as training a Random Forest model. The dataset is chronologically divided into training and testing sets to maintain temporal consistency. Model evaluation is conducted using Mean Absolute Error, Root Mean Squared Error, Mean Absolute Percentage Error, and the coefficient of determination. The results indicate that the Random Forest model provides strong predictive performance, achieving a Mean Absolute Error of 202.91, a Root Mean Squared Error of 260.83, a Mean Absolute Percentage Error of 2.13%, and a coefficient of determination of 0.85. Feature contribution analysis reveals that the 12-period Exponential Moving Average has the most dominant influence on the prediction results. Based on these findings, it can be concluded that the Random Forest method is effective for predicting stock prices based on technical indicators and has the potential to support investment decision-making.

Optimasi Software Effort Estimation Menggunakan Random Forest

Maria Rosario Borroek — 2026-04-30

Software development effort estimation is crucial as it is one of the key factors for successful software development. This research employs Random Forest to estimate software development effort. To achieve better results, the study combines the Random Forest method with Genetic Algorithm. The results show that the China dataset provides more accurate estimation compared to the Desharnais dataset, because the China dataset uses relevant feature selection for estimation

Pengembangan Game Berbasis Construct 3 Untuk Meningkatkan Minat dan Pemahaman Konsep IPA Pada Siswa Sekolah Dasar

Jefriansah — 2026-04-30

This study aims to develop an educational game titled “Ludo Cendekia” using Construct 3 to enhance elementary school students’ interest in and understanding of science concepts. The research method employed was Research and Development (R&D) using the ADDIE model, which comprises the stages of Analysis, Design, Development, Implementation, and Evaluation. Data collection was conducted through observation, interviews, and questionnaires administered to 19 students and 1 teacher at SD Negeri 067 Tanjab Barat. System testing was performed using Blackbox Testing to assess system functionality, as well as a User Acceptance Test (UAT) to measure user acceptance levels. The results of the study indicate that all system functions operate effectively and achieved a high level of user acceptance, with 65.49% strongly agreeing and 28.64% agreeing. These results demonstrate that the developed educational game is effective in enhancing student engagement and aiding their understanding of science concepts. This research contributes to the development of game-based interactive learning media that can serve as an alternative for science education in elementary schools

Perbandingan K-Means, DBSCAN, Agglomerative pada Clustering Gempa Bumi Sumbagsel 2015–2025 Berbasis USGS

Shafa Aurelliza Arian — 2026-04-30

Southern Sumatra is one of the most seismically active regions in Indonesia, situated along the Great Sumatran Fault and the Indo-Australian subduction zone, making systematic spatial analysis of earthquake data essential for effective disaster mitigation. This study conducts a comparative analysis of three clustering algorithms, namely K-Means, DBSCAN, and Agglomerative Clustering, applied to earthquake data in the southern Sumatra region for the period 2015–2025 sourced from the United States Geological Survey (USGS) catalog. A total of 2,483 earthquake events were analyzed after preprocessing, with key attributes including geographic coordinates (latitude and longitude) and hypocenter depth. Cluster quality was evaluated using Silhouette Score and Davies-Bouldin Index (DBI). Results show that K-Means achieved the best quantitative performance with a Silhouette Score of 0.4204 and DBI of 0.8715, followed by Agglomerative Clustering with a Silhouette Score of 0.4047 and DBI of 0.8789. DBSCAN could not be evaluated quantitatively due to noise point classification, yet effectively captured complex spatial patterns aligned with the subduction zone structure. All three methods consistently identified seismic activity concentrated along the southern Sumatra subduction zone, dominated by shallow to intermediate-depth earthquakes. These findings provide data-driven recommendations to support earthquake disaster mitigation planning in the southern Sumatra region

Komparasi Algoritma K-Means dan DBSCAN dalam Klasterisasi Kualitas Udara di Wilayah Jabodetabek Berdasarkan Indeks Standar Pencemar Udara

Ahmad Fadhil Rizqi — 2026-04-30

Air quality is a critical environmental issue because it directly impacts public health and the sustainability of urban environments. The Greater Jakarta area, as a hub of economic activity and population mobility, faces high levels of air pollution; however, a comprehensive understanding of air quality patterns remains limited due to the complexity of the data and the variation in pollutant parameters. This study aims to analyze and compare the performance of clustering algorithms in grouping air quality levels based on Air Pollutant Standard Index (ISPU) data in the Greater Jakarta area. The methods used were K-Means and DBSCAN with six input parameters PM2.5, PM10, SO₂, NO₂, O₃, and CO—which underwent data preprocessing, the clustering process, and evaluation using the Silhouette Score and the Davies-Bouldin Index (DBI). The results indicate that K-Means with three clusters yields the best performance, achieving a Silhouette Score of 0.324 and a DBI of 1.142, while DBSCAN achieves a Silhouette Score of 0.013 and a DBI of 1.240. These findings indicate that K-Means is more effective in forming cohesive groupings of air quality patterns and can be utilized as a basis for decision-making in the monitoring and control of urban air quality.

Implementasi MDLC pada Perancangan Spanduk UMKM Kuliner

Dwi Cahya Medika — 2026-04-30

This study aims to design and test the effectiveness of outdoor promotional banners for two culinary MSMEs with different characteristics, namely Ayam Geprek and Nasi Goreng. The method used is the Multimedia Development Life Cycle (MDLC) Luther-Sutopo version, consisting of six stages: Concept, Design, Material Collecting, Assembly, Testing, and Distribution. The results produced an Ayam Geprek banner prototype dominated by bright red nuances and bold typography to trigger "urgent" impulses and "taste challenges", while the Nasi Goreng banner utilizes warm brownish nuances and hot steam visualization to represent comfort and night warmth. Testing was validated using Roland Barthes' semiotic analysis to dissect the meaning of the graphic elements. In conclusion, the MDLC method is proven capable of producing promotional media with high aesthetic value, targeted visual communication, and readiness for integrated marketing distribution

Perancangan Arsitektur Enterprise Berbasis TOGAF ADM untuk Integrasi Sistem Pengelolaan Sampah Perumahan Pura Arista

Khansa Dzakiyyah Amany Aziz — 2026-04-30

Waste management in the Pura Arista residential area is still conducted manually through unstructured reporting, inefficient scheduling, and limited operational data documentation, resulting in difficulties in monitoring and low service transparency. This study aims to design an enterprise architecture to support the digital transformation of waste management using the TOGAF Architecture Development Method (ADM). A qualitative approach was employed through observation, semi-structured interviews, and document analysis to identify system requirements and existing problems. The results of this study are an enterprise architecture design covering business, data, application, and technology domains, proposing an integrated system consisting of a resident reporting application, a worker application, an administrative dashboard, and a centralized database connected through integration services. Validation was conducted using expert review and requirement traceability analysis, indicating that the proposed architecture aligns with operational needs and has the potential to improve efficiency, data traceability, and service transparency. Therefore, the proposed architecture can serve as a foundation for developing a more structured and adaptive waste management system in residential environments.