cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Aslan
Contact Email
aslanalbanjary066@gmail.com
Phone
+6281389102026
Journal Mail Official
aslanalbanjary066@gmail.com
Editorial Address
Jalan. H. Muckhsin Dusun Tanjung Mentawa, Tanjung Mekar Sambas Village, West Kalimantan, Indonesia
Location
Kab. sambas,
Kalimantan barat
INDONESIA
Prosiding Seminar Nasional Indonesia
Published by CV. Adiba Aisha Amira
ISSN : -     EISSN : 30265169     DOI : -
Core Subject : Humanities, Education, Social,
Humanities Social Sciences Other
Prosiding Nasional Adisam dapat menerima naskah dalam bidang-bidang seperti pendidikan, kesehatan, hukum, ekonomi, teknologi informasi (Teknik Informatika), teknik sipil, teknik elektro, teknik mesin, perikanan, pertanian, ilmu sosial-humaniora, dan bidang-bidang ilmu lainnya.
Arjuna Subject : Ilmu Sosial - Ilmu Sosial (Lain-Lain)
Articles 135 Documents
 10   11   12   13   14 
ANALISIS KOMPARASI ALGORITMA RANDOM FOREST, XGBOOST, DAN MULTILAYER PERCEPTRON (MLP) DALAM PREDIKSI RISIKO GAGAL BAYAR KREDIT D. Febry Wulangsih; Keysya Alifia Zabina
Prosiding Seminar Nasional Indonesia Vol. 4 No. 1 (2026): Prosiding Seminar Nasional Indonesia
Publisher : CV. Adiba Aisha Amira

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.20742401

Abstract

Credit risk prediction is a critical task for financial institutions in identifying customers at risk of default. This study compares the performance of three machine learning and deep learning algorithms as in Multilayer Perceptron (MLP), Random Forest, and XGBoost in predicting credit card defaults using the “Default of Credit Card Clients” dataset from the UCI Machine Learning Repository. The dataset consists of 30,000 records with 23 features covering demographic information, payment history, bills, and payment amounts over a six-month period. Class imbalance was addressed using the Synthetic Minority Oversampling Technique (SMOTE), which was applied only to the training data. Model performance was evaluated using accuracy, precision, recall, F1-score, and AUC-ROC metrics. The experimental results show that Random Forest achieved the best overall performance with an F1-score of 0.5275 and an AUC-ROC of 0.768, outperforming MLP (F1-score 0.5182, AUC-ROC 0.7610) and XGBoost (F1-score 0.5080, AUC-ROC 0.7616%). These findings indicate that ensemble-based methods remain competitive compared to deep learning approaches for tabular credit data, and provide valuable insights for financial institutions in implementing data-driven risk management.
PERAMALAN PENJUALAN AKI MENGGUNAKAN ARIMA UNTUK REKOMENDASI SAFETY STOCK Rafi Argya Dharma H; Haqi Achmad Farizky
Prosiding Seminar Nasional Indonesia Vol. 4 No. 1 (2026): Prosiding Seminar Nasional Indonesia
Publisher : CV. Adiba Aisha Amira

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.20742428

Abstract

Inventory uncertainty is one of the main operational challenges faced by retail businesses, including automotive battery stores. Inaccurate inventory planning can lead to overstock and stockout conditions, both of which negatively affect operational efficiency and customer satisfaction. This study aims to forecast battery sales using the Autoregressive Integrated Moving Average (ARIMA) model as the basis for determining Safety Stock and Reorder Point (ROP) at Toko Aki Restu. The research adopts the CRISP-DM framework consisting of Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment stages. Historical monthly sales data from October 2024 to October 2025 were analyzed using the ARIMA method. The results showed that ARIMA(1,0,2) was the best forecasting model based on the smallest Akaike Information Criterion (AIC) value. The evaluation process generated MAE of 9.85, RMSE of 12.27, and MAPE of 5.3%, indicating that the forecasting model had very high accuracy. Forecasting results were then utilized to calculate Safety Stock and Reorder Point values. The study produced a Safety Stock recommendation of 10 units and a Reorder Point of 54 units. Furthermore, the forecasting and inventory recommendations were visualized through a web-based dashboard to support operational decision-making. The implementation of this study is expected to help the company minimize inventory risks and improve stock management efficiency.
INOVASI APLIKASI MOBILE BERBASIS KECERDASAN BUATAN PADA LAYANAN DINAS SOSIAL PROVINSI JAWA TIMUR MENGGUNAKAN METODE RAPID APPLICATION DEVELOPMENT Kandhi Surya Atmadja
Prosiding Seminar Nasional Indonesia Vol. 4 No. 1 (2026): Prosiding Seminar Nasional Indonesia
Publisher : CV. Adiba Aisha Amira

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.20742456

Abstract

Delivering public services and social aid frequently faces hurdles regarding data precision and information access. This research focuses on the creation of a React Native-based mobile app prototype equipped with an AI chatbot, functioning as a digital information hub for the East Java Provincial Social Services. The study utilizes the Rapid Application Development (RAD) methodology, encompassing Requirements Planning, User Design (UI/UX with Figma), Construction (frontend with React Native, backend via Supabase, and AI training), and Cutover phases. This rapid iterative process produces the E-JSC application, a versatile platform featuring an AI chatbot ("Tanya JSC"), social aid transparency dashboards ("SapaBansos"), and online permit services. By incorporating Artificial Intelligence, the system autonomously handles frequent public questions, thereby minimizing queues at service centers. Ultimately, this mobile solution effectively upgrades public service operations, guaranteeing that social aid details remain precise, reachable, and well-managed.
PENGEMBANGAN ANTARMUKA WEBSITE E-COMMERCE TOKO-TOPIA BERBASIS KOMPONEN MENGGUNAKAN REACTJS Muhammad Rifki Syahada
Prosiding Seminar Nasional Indonesia Vol. 4 No. 1 (2026): Prosiding Seminar Nasional Indonesia
Publisher : CV. Adiba Aisha Amira

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.20742465

Abstract

This project aims to design and develop a responsive and interactive e-commerce website user interface (UI) named Toko-Topia using ReactJS. By utilizing this modern JavaScript library, the development focuses on performance, user experience (UX), and ease of navigation for customers. The developed website features functionalities such as product search, a shopping cart system, and API integration for checkouts, providing an optimal online shopping experience. This technology also enables efficient component management, supports real-time data updates, and enhances application scalability. The implementation of ReactJS in this e-commerce website development offers a modern solution for businesses to enhance their digital presence. The results of this project are expected to contribute to improving user experience in online shopping while supporting the growth of the digital economy in Indonesia.
KLASTERISASI POLA PERMINTAAN PADA UMKM MENGGUNAKAN DATA TRANSFORMATION DAN K-MEANS CLUSTERING Lailaturahma Maulidah; Achmad Mukhlis
Prosiding Seminar Nasional Indonesia Vol. 4 No. 1 (2026): Prosiding Seminar Nasional Indonesia
Publisher : CV. Adiba Aisha Amira

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.21756576

Abstract

The consumer electronics retail industry is characterized by short product life cycles and intermittent demand patterns at the stock keeping unit (SKU) level. This study performs demand pattern segmentation of SKUs at an electronics retail store using the Average Demand Interval (ADI) and Squared Coefficient of Variation (CV²) features extracted from three years of transaction data. Both features were transformed using log1p and Z-score standardization to address the skewed data distribution, and then clustered using the K-Means algorithm with candidate values of K ranging from 2 to 4. The optimal number of clusters was selected based on the Silhouette Score and Davies-Bouldin Index (DBI), while segment labeling was performed using empirical median thresholds derived from the research data, rather than the standard Syntetos-Boylan-Croston cut-off values. Results on 1,342 valid SKUs show that K=2 is the optimal number of clusters (Silhouette Score 0.6380; DBI 0.7034), which were interpreted as the "routine-stable demand" segment (1,055 SKUs; 78.61%) and the "routine but fluctuating" segment (287 SKUs; 21.39%), with the separation being more dominated by ADI values than by CV². These findings indicate that the demand structure is more accurately represented by two transaction-frequency-based groups, and can serve as a basis for inventory management policies tailored to the characteristics of each segment.

Page 14 of 14 | Total Record : 135

 10   11   12   13   14 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 1 (2026): Prosiding Seminar Nasional Indonesia Vol. 3 No. 3 (2026): Prosiding Seminar Nasional Indonesia Vol. 3 No. 2 (2025): JUNI Vol. 3 No. 1 (2025): Prosiding Seminar Nasional Indonesia Vol. 2 No. 3 (2025): Prosiding Seminar Nasional Indonesia Vol. 2 No. 2 (2025): Prosiding Seminar Nasional Indonesia Vol. 2 No. 1 (2024): Prosiding Seminar Nasional Indonesia Vol. 1 No. 3 (2024): Prosiding Seminar Nasional Indonesia Vol. 1 No. 2 (2024): Prosiding Seminar Nasional Indonesia Vol. 1 No. 1 (2023): Prosiding Seminar Nasional Indonesia