Article Per Year (5 Year)
p-Index From 2020 - 2025
2.293
P-Index
This Author published in this journals
All Journal Journal of Information Systems Engineering and Business Intelligence Journal of Dedicators Community Jurnal Abdimas PHB : Jurnal Pengabdian Masyarakat Progresif Humanis Brainstorming bit-Tech Jurnal Informatika dan Rekayasa Perangkat Lunak Jurnal Abdi Insani Jurnal Teknologi Informasi dan Komunikasi INSERT: Information System and Emerging Technology Journal Biner : Jurnal Ilmiah Informatika dan Komputer SmartComp Integrasi : Jurnal Ilmiah Teknik Industri LogicLink: Journal of Artificial Intelligence and Multimedia in Informatics
Sabilla, Alzena Dona
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Public Health Social Sciences

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
DIGITAL INTEREST DAN TALENT MAPPING DALAM PENINGKATAN MANAJEMEN LAYANAN LEMBAGA DI MTS AL ISLAM JEPARA Saefudin, Ahmad; Rofiqoh, Naili; Sabilla, Alzena Dona; Laila, Azzah Nur; Candraloka, Olyvia Revalita; Rosyidah, Afifatur; Firmansyah, Andre
Jurnal Abdi Insani Vol 12 No 9 (2025): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v12i9.2928

Abstract

The rapid development of technology requires educational institutions to adapt by utilizing digitalization to improve services and learning quality. One urgent need is student interest and talent mapping as well as strengthening institutional branding that is relevant in the digital era. MTs Al Islam Jepara, as a private educational institution, faces challenges in service management and promotion, thus requiring strategic steps through training activities. The purpose of this activity is to enhance teachers’ competence in digital-based talent mapping and to develop effective institutional branding strategies. The method was carried out in three stages: socialization, training, and evaluation. The training included capacity building in student talent mapping and institutional branding with digital promotion strategies. The results show an improvement in teachers’ understanding and skills in identifying students’ interests and talents more systematically, as well as their ability to manage institutional branding strategies through digital media. Participants stated that the program was relevant to the school’s needs, beneficial for improving service quality, and strengthened the institution’s readiness to face modern educational challenges. Evaluation indicated positive responses, with most participants assessing the trainers as competent, materials as easy to understand, and facilities as adequate, although a longer training duration was considered necessary. In conclusion, this community service program successfully improved teachers’ capacity in talent mapping and digital branding, thereby achieving the goal of strengthening educational service management.
Optimasi Prediksi Penjualan di Industri Meubel Menggunakan Double Exponential Smoothing Amrita, Leni; Sabilla, Alzena Dona; Minardi, Joko
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 14, No 4 (2025): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v14i4.8476

Abstract

Penelitian ini bertujuan untuk mengoptimalkan prediksi penjualan di industri meubel dengan menggunakan metode Double Exponential Smoothing (DES). Metode ini dipilih karena mampu menganalisis data historis dengan mempertimbangkan tren dan pola musiman, sehingga mampu menghasilkan prediksi yang lebih akurat. Data yang digunakan dalam penelitian ini berasal dari penjualan meubel tahun 2023 yang diambil dari platform Kaggle, mencakup informasi bulanan untuk produk seperti sofa, arm chair, cabinet, single door, dan cladding. Penelitian ini dilakukan melalui beberapa tahapan mulai dari pengumpulan data, pra-pemrosesan, hingga perhitungan prediksi meggunakan metode DES. Evaluasi model dilakukan menggunakan metrik Mean Absolute Percentage Error (MAPE) untuk mengukur tingkat akurasi prediksi. Hasil penelitian menunjukkan bahwa setiap produk memiliki nilai parameter smoothing (α) optimal dengan tingkat kesalahan terkecil, produk sofa memiliki MAPE terkecil sebesar 3,961% pada α = 0,5, arm chair sebesar 5,691% pada α = 0,6, cabinet sebesar 12,517% pada α = 0,6, single door sebesar 18,583% pada α = 0,5, dan cladding sebesar 8,122% pada α = 0,5. Untuk mempermudah proses perhitungan dan analisis, sistem berbasis web dirancang untuk menyajikan hasil prediksi secara visual dan interaktif. Sistem ini membantu perusahaan menyusun strategi stok dan perencanaan penjualan berdasarkan prediksi yang akurat. Penelitian ini menunjukkan bahwa metode DES efektif dalam meningkatkan efisiensi operasional perusahaan dan memperkuat daya saing di pasar meubel yang kompetitif.
Academic Guidebook Chatbot: Performance Comparison of Fine-Tuned Mistral 7B and LlaMA-2 7B Rachman, Davied Indra; Akbar, Agus Subhan; Sabilla, Alzena Dona
Journal of Information Systems Engineering and Business Intelligence Vol. 11 No. 3 (2025): October
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.11.3.383-392

Abstract

Background: Chatbot is recently ranked as the main technological solution due to the high demand for fast and efficient information retrieval. Therefore, this study was carried out to develop a local document-based chatbot that can answer questions related to the contents of PDF documents using open-source AI models such as Mistral 7B and LLaMA-2 7B. Although these models were effective at processing natural language, a major challenge was observed in the tendency to generate hallucinated answers, characterized by having inaccuracies and being out of context. Objective: This study aims to reduce hallucinatory responses from chatbot models by making their responses more precise and accurate through fine-tuning. The performance of fine-tuned models (Mistral 7B and LLaMA-2 7B) was also compared. Methods: Fine-tuning of the two models was performed using domain-specific datasets taken from Academic Guidebook. This process was conducted to improve models ability to understand and answer questions relevant to Academic Guidebook context. Performance was evaluated using METEOR Score to measure literal agreement and BERTScore to assess meaning agreement. In addition, response time was measured to assess efficiency, while chatbot system was developed using Streamlit and LangChain for real-time interaction. Results: Fine-tuned Mistral 7B model achieved the highest METEOR value of 0.40 and F1 of 0.78 based on BERTScore results. Regarding efficiency, fine-tuned Mistral 7B showed a faster response time than LLaMA-2. Meanwhile, the non-fine-tuned Mistral 7B and LLaMA-2 7B showed a longer response time than fine-tuned Mistral 7B and LLaMA-2 7B. Conclusion: The results showed that the enhancements significantly improved the performance of large language models in specific tasks, reduced hallucinations, and enhanced response quality Keywords: Chatbot, Large Language Model, Mistral 7B, LLaMA-2 7B, METEOR Score
PENERAPAN BUSINESS INTELLIGENCE SYSTEM PADA TRANSAKSI AGEN BRILINK FIANCELLULER Sabilla, Alzena Dona; Yoga, Hendra Tri; Saputro, Heru
LogicLink Vol. 1 No. 1, June 2024
Publisher : Universitas Islam Negeri K.H. Abdurrahman Wahid Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28918/logiclink.v1i1.8466

Abstract

Fiancelluler brilink agent is a business engaged in the service sector. The services offered by brilink fiancelluler agents are serving money transfers, cash withdrawals and multipayment payments. This study aims to apply business intelligence to the transaction information system for brilink fiancelluler agents which is implemented in the form of reporting dashboards as a reference for decision making at brilink fiancelluler agents. The method used is FAST (Framework for the Application System Thinking). With stages: scope definition, problem analysis, requirements analysis, logical design and physical design. The results of this study are in the form of a reporting dashboard that contains information about transactions at brilink fiancelluler agents in the form of completed transactions, transaction graphs, transaction details, transaction types, frequently used banks and gender. Testing on the fiancelluler brilink agent system uses 2 methods. First testing with the black box method with 8 tests with no results found errors or the system works according to orders. Both usability methods with 4 aspects of testing namely learnability, flexibility, effectiveness, attitude with 40 respondents. The results obtained from the usability testing method are 84.22% very suitable for use by consumers
E-SCM SEBAGAI STRATEGI PENGENDALIAN PERSEDIAAN DI INDUSTRI FURNITURE Sabilla, Alzena Dona; mahendra, Danang; Azzat, Noor Nailie; Ananta, Yoga Sofian
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 16 No. 1 (2025): MARET
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/rjqa0p56

Abstract

Digitalization and globalization have a big impact on the furniture industry, especially on the MSME scale. A big challenge in managing product inventory efficiently. Mismanagement of product stock can lead to high operational costs and decreased customer satisfaction. This research aims to develop a web-based Electronic Suppy Chain Management (E-SCM) application to improve inventory control in Furniture MSMEs. This application is equipped with main features such as managing products, managing incoming and outgoing stock items, and a dashboard tang displaying stock movements in real time. Case studies were conducted on 10 furniture MSMEs in Jepara, using sales and inventory data for 12 months. Data analysis shows that the application of the E-SCM application increases the accuracy of stock management, reduces the amount of dead stock and accelerates the process of making business decisions. This research is expected to be a reference for E-SCM-based technology development for other MSME sectors.
SISTEM INFORMASI DIAGNOSA STUNTING BALITA MENGGUNAKAN METODE FORWARD CHAINING PADA DP3AP2KB JEPARA Huda, Muhammad Nidhomul; Sabilla, Alzena Dona; Minardi, Joko
Biner : Jurnal Ilmiah Informatika dan Komputer Vol 3 No 1 (2024): Januari
Publisher : Program Studi Teknik Informatika, Fakultas Teknik dan Ilmu Komputer, Universitas Sains Al-Qur'an

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32699/biner.v3i1.6625

Abstract

Sistem informasi menjadi salah satu hal yang penting bagi suatu instansi dalam pengelolaan data, khususnya dalam hal ini informasi perkembangan balita pada DP3AP2KB Jepara. Stunting merupakan suatu kondisi gagal tubuh akibat kekurangan nutrisi dan gizi kronis, yang dapat diketahui melalui panjang dan berat badan yang tidak normal. Penelitian ini bertujuan untuk membangun sistem informasi diagnosa stunting pada Balita menggunakan metode forward chaining. Dalam pengembangannya menggunakan bahasa pemrograman PHP dengan database Mysql untuk penyimpanan datanya. Sistem ini membantu dalam melakukan diagnosa stunting pada balita melalui penginputan tinggi badan dan berat badan yang dilakukan oleh kader setiap bulan di posyandu. Selain itu, sistem ini juga memberikan solusi apabila ada balita yang terindikasi stunting. Sistem ini dapat digunakan dimana saja dan kapan saja, baik oleh tenaga kesehatan, kader posyandu maupun oleh orang tua, sehingga dapat membantu keterbatasan masalah deteksi dini tumbuh kembang yang sebelumnya hanya dapat dilakukan oleh tenaga kesehatan.
Co-Authors Agus Subhan Akbar, Agus Subhan Ahmad Saefudin Amrita, Leni Ananta, Yoga Sofian Danang Mahendra, Danang Firmansyah, Andre Huda, Muhammad Nidhomul Joko Minardi, Joko Laila, Azzah Nor Laila, Azzah Nur Margaretha, Sintikhe Novia Maulana, Irvan Noor Azizah Noor Nailie Azzat Olyvia Revalita Candraloka, Olyvia Revalita Pratama, Andrian Dico Rachman, Davied Indra Rofiqoh, Naili Rosyidah, Afifatur Sabrina, Dinta saputro, heru Suluh, Reyvaldo Febrian Rizki Yoga, Hendra Tri