Muhamad Andri Rian Riyadi
Universitas Pamulang

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

Found 2 Documents
Search

Analisis dan Perancangan Sistem Informasi Manajemen BUMDes Berbasis Website Menggunakan Standar ISO/IEC 25010 Aldy Bifal Pratama; Muhamad Andri Rian Riyadi; Chairul Anwar
Journal of Information Systems and Business Technology Vol 2 No 3 (2026): Journal of Information Systems and Business Technology
Publisher : PT Jurnal Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The village economy is strategically driven by village-owned enterprises (BUMDes), but accountability and transparency are frequently hampered by manual data administration. The analysis and construction of a web-based BUMDes Management Information System are the goals of this project. Digitising the company's inventory, financial reporting, and administrative procedures is the aim. Because it enables BUMDes developers and managers to work closely together to identify user demands by gradually iterating the interface and functionality design, the prototype system development method was used for this study. By doing this, the likelihood of system incompatibility during the last step of implementation is decreased.The international standard ISO/IEC 25010 is used to guarantee the quality of the software produced. The primary subjects of testing are functional suitability, performance efficiency, ease of use, and reliability. A systematic and scalable information system model that may enhance BUMDes operations' efficiency and support data-driven decision-making is anticipated as a result of this design.
Analisis Data Mining Menggunakan Metode Regresi Linier untuk Estimasi Nilai Hunian pada Dataset California Housing Dinnar Rizky; Muhamad Andri Rian riyadi
Journal of Information Systems and Business Technology Vol 2 No 3 (2026): Journal of Information Systems and Business Technology
Publisher : PT Jurnal Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The property sector has highly fluctuating price dynamics, influenced by various factors ranging from geographical conditions to building facilities. Accurate housing price estimation is essential for developers and prospective buyers to make informed decisions. This study aims to apply Data Mining techniques using the Linear Regression algorithm to estimate the median value of housing in the California Housing dataset. This research methodology follows the stages of knowledge discovery in databases, which include data cleaning, data integration, transformation, and modeling. The dataset is processed by conducting correlation analysis to determine the main predictor variables, such as median income, geographic location, and population density. A Linear Regression model is built to map the relationship between these independent variables and the value of housing as the dependent variable. Model performance is evaluated using the statistical metrics Mean Absolute Error (MAE) and Coefficient of Determination ($R^2$). The results of the study are expected to show that Linear Regression is able to provide significant estimates with a reliable level of accuracy, where the median income variable is predicted to be the most dominant factor in determining house prices. This research contributes to the use of machine learning for more objective and efficient real estate market analysis.   Sektor properti memiliki dinamika harga yang sangat fluktuatif, dipengaruhi oleh berbagai faktor mulai dari kondisi geografis hingga fasilitas bangunan. Estimasi harga hunian yang akurat sangat diperlukan oleh pengembang dan calon pembeli untuk pengambilan keputusan yang tepat. Penelitian ini bertujuan untuk menerapkan teknik Data Mining menggunakan algoritma Regresi Linier untuk melakukan estimasi nilai tengah hunian pada dataset California Housing.Metodologi penelitian ini mengikuti tahapan penemuan pengetahuan dalam basis data (Knowledge Discovery in Databases), yang meliputi data cleaning, integrasi data, transformasi, hingga pemodelan. Dataset diproses dengan melakukan analisis korelasi untuk menentukan variabel prediktor utama, seperti pendapatan median (Median Income), lokasi geografis, dan kepadatan penduduk. Model Regresi Linier dibangun untuk memetakan hubungan antara variabel-variabel independen tersebut dengan nilai hunian sebagai variabel dependen.Kinerja model dievaluasi menggunakan metrik statistik Mean Absolute Error (MAE) dan Coefficient of Determination ($R^2$). Hasil penelitian diharapkan menunjukkan bahwa regresi linier mampu memberikan estimasi yang signifikan dengan tingkat akurasi yang dapat diandalkan, di mana variabel pendapatan median diprediksi menjadi faktor paling dominan dalam menentukan harga rumah. Penelitian ini memberikan kontribusi dalam pemanfaatan machine learning untuk analisis pasar real estat yang lebih objektif dan efisien.