Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND OFFICIAL STATISTICS
Hulliyyatus Suadaa, Lya
Unknown Affiliation
Computer Science & IT

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

Found 2 Documents
Search

 1 
An Intelligent Conversational Agent Using Self-Reflective Retrieval-Augmented Generation for Enhanced Large Language Model Support in National Accounts Learning Farhan, Muhammad; ., Yunofri; Tasriah, Etjih; Hulliyyatus Suadaa, Lya; Pramana, Setia
Proceedings of The International Conference on Data Science and Official Statistics Vol. 2025 No. 1 (2025): Proceedings of 2025 International Conference on Data Science and Official St
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/icdsos.v2025i1.575

Abstract

BPS Statistics Indonesia plays a strategic role in compiling balance sheet statistics as the foundation for national policy analysis. This role requires a deep understanding of the concepts, definitions, and compilation standards outlined in the System of National Accounts (SNA) manual. However, in practice, comprehending such complex technical documents is not always straightforward. To address this challenge, this study proposes the development of an intelligent conversational agent in the form of a chatbot that implements the Self-Multimodal RAG approach. This approach integrates self-reflection mechanisms to generate more accurate and relevant responses. The evaluation was conducted using the LLM-as-a-Judge framework across four metrics: answer correctness, answer relevancy, context relevancy, and context faithfulness. Experimental results demonstrate that the Self-Reflective RAG achieved a score of 80% on the answer correctness metric, with competitive performance in terms of relevancy and faithfulness. From the chatbot implementation perspective, black-box testing confirmed that all functionalities operated as expected, while system usability testing using the CSUQ instrument yielded a score of 74.704%, indicating that the chatbot is well-accepted by users.
Business Description Categorization to the Five-Digit Indonesian Standard Classification of Business Field (KBLI) Using Machine Learning and Transfer Learning Amnur, Muh. Alfian; Muhammad Gazali, La Ode; Mumtaz Siregar, Amir; Ariya Jalaksana, Faruq; Nisa Rahayu Ananda Suwendra, Made; Fadila Utami, Nurul; Median Ramadhan, Alif; Krisela Fabrianne, Elisse; Wirata Raja Panjaitan, Eurorea; Aini Izzati, Fitri; Bintang Yuliani Manalu, Jernita; Gilang Hidayat, Muhammad; Hulliyyatus Suadaa, Lya; Yuniarto, Budi; Pramana, Setia
Proceedings of The International Conference on Data Science and Official Statistics Vol. 2025 No. 1 (2025): Proceedings of 2025 International Conference on Data Science and Official St
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/icdsos.v2025i1.719

Abstract

The Indonesian Standard Classification of Business Fields (KBLI) is essential for economic statistics, yet manual classification of business descriptions to five-digit KBLI codes is time-consuming and prone to inconsistencies. This study aims to develop and compare machine learning (Support Vector Machine and Random Forest) and transfer learning  (IndoBERT) models for automating KBLI classification, supported by the preparation of synthetic and real-world datasets for model training. The synthetic data were generated using large language models, validated through human majority voting and complemented with realworld data from the National Labor Force Survey (Sakernas) and the Micro and Small Industry Survey (IMK). The findings indicate that Fine-tuned IndoBERT achieved superior performance, achieving an F1-score of 92.99% and an accuracy of 93.40% on synthetic data, alongside top-1, top-5, and top-10 accuracies of 32.93%, 54.71%, and 63.24% on real-world data. The deployment of fine-tuned IndoBERT as a RESTful API demonstrates its scalability and efficiency, presenting a reliable solution for large-scale KBLI classification in official statistics. 
Co-Authors ., Yunofri Aini Izzati, Fitri Amnur, Muh. Alfian Ariya Jalaksana, Faruq Bintang Yuliani Manalu, Jernita Fadila Utami, Nurul Gilang Hidayat, Muhammad Krisela Fabrianne, Elisse Median Ramadhan, Alif Muhammad Farhan Muhammad Gazali, La Ode Mumtaz Siregar, Amir Nisa Rahayu Ananda Suwendra, Made Pramana, Setia Tasriah, Etjih Wirata Raja Panjaitan, Eurorea Yuniarto, Budi