Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Jurnal Nasional Komputasi dan Teknologi Informasi International Journal of Basic and Applied Science Jurnal Ilmiah Sistem Informasi
Simbolon, Agata Putri Handayani
Unknown Affiliation
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Neuroscience Physics Transportation

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Advancing Decision-Making: AI-Driven Optimization Models for Complex Systems Sihotang, Hengki Tamando; Sihotang, Jonhariono; Simbolon, Agata Putri Handayani; Panjaitan, Firta Sari; Simbolon, Roma Sinta
International Journal of Basic and Applied Science Vol. 13 No. 3 (2024): Dec: Optimization and Artificial Intelligence
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/ijobas.v13i3.581

Abstract

Effective decision-making in complex systems requires optimization models that balance multiple competing objectives, such as cost efficiency, time constraints, and adaptability to dynamic environments. This research proposes an AI-driven optimization model utilizing the Pareto optimization algorithm to enhance decision-making accuracy and system resilience. The model was tested in a logistics scenario, demonstrating a 10% reduction in operational costs and a 36% decrease in time deviations while improving adaptability to real-time disruptions. Unlike traditional static models, the proposed framework dynamically adjusts to external factors, optimizing resource allocation and route planning in real-world conditions. The findings highlight the model’s capability to bridge the gap between theoretical AI advancements and practical applications in industries such as supply chain management, urban transportation, and disaster response logistics. While computational requirements and data availability pose challenges, future research should explore computational efficiency enhancements, broader industry applications, and sustainability integration. This study contributes to the advancement of AI-based multi-objective optimization, providing a scalable and adaptable solution for complex decision-making in dynamic environments
Early warning systems for financial distress: A machine learning approach to corporate risk mitigation Judijanto, Loso; Sihotang, Jonhariono; Simbolon, Agata Putri Handayani
International Journal of Basic and Applied Science Vol. 13 No. 1 (2024): June: Basic and Aplied Science
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/ijobas.v13i1.470

Abstract

This research explores the development of an early warning system for corporate financial distress using machine learning techniques to address key challenges in corporate risk mitigation. The main objective is to enhance predictive accuracy by integrating financial and non-financial data, addressing class imbalance, and ensuring model interpretability. The research design involves the formulation of a new machine learning model, leveraging cost-sensitive learning and feature selection, and is tested with a numerical example using logistic regression. Methodologically, the study adopts a data-driven approach that incorporates diverse financial ratios, macroeconomic variables, and market sentiment indicators to predict corporate distress. The numerical results from a basic logistic regression model demonstrate poor performance, especially in handling class imbalance, revealing limitations in traditional statistical models. However, the research suggests that machine learning methods, particularly ensemble learning with cost-sensitive algorithms, offer superior predictive accuracy and practical applicability. The study concludes that integrating advanced techniques and diverse datasets leads to more reliable early warning systems, with significant implications for corporate governance and financial risk management. Future research should explore more sophisticated machine learning models and extend real-world applications across various industries and economic conditions.
Development of the Andana Mobile Application: An Interactive Japanese Language Learning Platform Using Flutter and Firebase Halawa, Sovantri Putra Paskah; Sinaga, Rizal Muslim; Simbolon, Agata Putri Handayani; Priscilia, Selfi Audy; Perdana, Adidtya
Jurnal Ilmiah Sistem Informasi Vol. 4 No. 3 (2025): November: Jurnal Ilmiah Sistem Informasi
Publisher : LPPM Universitas Sains dan Teknologi Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/0m972c26

Abstract

Peningkatan minat masyarakat Indonesia terhadap bahasa Jepang mendorong kebutuhan akan media pembelajaran yang lebih interaktif dan fleksibel. Namun, banyak aplikasi yang tersedia masih terbatas pada penyajian materi tanpa sistem progres belajar yang adaptif. Penelitian ini bertujuan untuk mengembangkan aplikasi mobile “Andana” sebagai platform pembelajaran bahasa Jepang interaktif berbasis Flutter dan Firebase. Metode penelitian yang digunakan adalah Research and Development (R&D) dengan pendekatan software engineering. Proses pengembangan mencakup analisis kebutuhan, perancangan sistem, implementasi, dan pengujian fungsional. Data penelitian bersumber dari hasil uji coba fungsionalitas dan evaluasi performa aplikasi oleh pengguna. Aplikasi Andana dirancang dengan dua peran utama, yaitu pengguna dan admin, serta dilengkapi fitur pembelajaran berbasis multimedia (PDF, video, audio), flashcard, latihan mendengarkan, berbicara, dan sistem catatan pribadi. Hasil penelitian menunjukkan bahwa seluruh fungsi aplikasi berjalan dengan baik, dengan sinkronisasi data real-time dan tampilan antarmuka yang responsif. Integrasi antara Flutter dan Firebase terbukti mendukung pengelolaan data pengguna dan pembaruan konten secara dinamis. Kontribusi penelitian ini terletak pada pengembangan model aplikasi pembelajaran berbasis cloud yang adaptif dan mudah dikembangkan. Implikasinya, aplikasi Andana berpotensi menjadi media belajar bahasa Jepang yang efisien, menarik, serta dapat diadaptasi untuk bahasa asing lainnya di masa mendatang.
Analisis Kinerja Sistem Transportasi Daring: Simulasi Dampak Ukuran Armada dan Algoritma Penugasan Terhadap Waktu Tunggu Pelanggan Alfahri, Muhammad Rizki; Indra, Zulfahmi; Sinaga, Rizal Muslim; Simbolon, Agata Putri Handayani
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 6 (2025): Desember 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i6.9895

Abstract

Abstrak - Mobilitas perkotaan modern bergantung pada layanan transportasi online.  Optimasi ukuran armada dan algoritma penugasan sangat penting untuk kinerja sistem ini; namun, penelitian empiris tentang perbedaan antara kedua komponen tersebut masih sedikit.  Studi ini menggunakan simulasi komputer untuk melihat bagaimana interaksi antara ukuran armada dan algoritma penugasan berdampak pada waktu tunggu pelanggan.  Studi ini menguji 24 skenario yang menggabungkan 8 ukuran armada (3–30 driver) dan 3 algoritma penugasan (paling dekat, pengaturan acak, dan berbasis queue).  Algoritma driver paling dekat mengurangi waktu tunggu rata-rata sebesar 41,6 persen dibandingkan dengan random assignment, dan setiap simulasi dijalankan selama 150 langkah waktu.  Dengan service rate 100%, armada 25 driver mencapai zero waiting time. Studi ini menunjukkan bukti nyata bahwa kinerja sistem transportasi online dapat secara signifikan ditingkatkan dengan mengoptimalkan kombinasi armada dan algoritma.  Untuk mencapai tingkat efisiensi operasional terbaik, disarankan untuk menggunakan algoritma driver terdekat dengan armada 20 hingga 25 driver.Kata kunci: Transportasi Daring; Optimasi Armada; Algoritma Penugasan; Waktu Tunggu; Simulasi Agent-based; Abstract - Modern urban mobility depends on online transportation services.  Optimizing fleet size and assignment algorithms is critical to the performance of these systems; however, empirical research on the differences between these two components is still scarce.  This study uses computer simulations to examine how the interaction between fleet size and assignment algorithms affects customer wait times.  The study tested 24 scenarios combining 8 fleet sizes (3–30 drivers) and 3 assignment algorithms (nearest driver, random assignment, and queue-based).  The nearest driver algorithm reduced average waiting time by 41.6 percent compared to random assignment, and each simulation ran for 150 time steps.  With a service rate of 100%, a fleet of 25 drivers achieved zero waiting time. This study provides clear evidence that the performance of online transportation systems can be significantly improved by optimizing the combination of fleet size and algorithm. To achieve the highest level of operational efficiency, it is recommended to use the nearest driver algorithm with a fleet size of 20 to 25 drivers.Keywords: Online Transportation; Fleet Optimization; Assignment Algorithm; Waiting Time; Agent-based Simulation;
Co-Authors Adidtya Perdana, Adidtya Alfahri, Muhammad Rizki Halawa, Sovantri Putra Paskah Hengki Tamando Sihotang Judijanto, Loso Panjaitan, Firta Sari Priscilia, Selfi Audy Sihotang, Jonhariono Simbolon, Roma Sinta Sinaga, Rizal Muslim Zulfahmi Indra, Zulfahmi