Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal International Journal of Social Service and Research Journal of Management, Economic, and Financial
Fhrizz S. De Jesus
College of Management and Business Technology, NEUST, Philippines
Humanities Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Social Sciences

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

Found 2 Documents
Search

 1 
Web-Based Electronic Goods Sales Application Design Rafi Farizki; Lutfi Mualiman; Freddy Wicaksono; Fhrizz S. De Jesus; Meritorious Autonomous; Vo Hung Cuong
International Journal of Social Service and Research Vol. 2 No. 8 (2022): International Journal of Social Service and Research (IJSSR)
Publisher : Ridwan Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46799/ijssr.v2i8.155

Abstract

The development of technology, especially internet-based technology, is increasing, including sales information system technology or so-called web online stores that can be used to purchase products simply by logging into the web, selecting the preferred goods and paying using a transfer system, the goods will be delivered to the address which is aimed. In Indonesia, the development of sales information systems is very reasonable and will continue to increase rapidly with the spread of the internet to all corners of the region. The purpose of this research is to know that this sales application system can already be used online. The method used is to use system design analysis. The results showed that in making these electronic goods sales application using the PHP programming language with MYSQL Database. The application for selling electronic goods is also known to have three important aspects, namely: login menu, admin dashboard, and payment page.
Hybrid Retrieval-Augmented Generation with Hallucination Mitigation for Indonesian MSME Financial Advisory Rafi Farizki; Rani Santika; Fhrizz S. De Jesus
Journal of Management Economic and Financial Vol. 4 No. 2 (2026): Journal of Management, Economic and Financial
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jmef.v4i2.203

Abstract

Micro, small, and medium enterprises (MSMEs) are the backbone of Indonesia's economy, yet many owners face persistent gaps in financial literacy and difficulty navigating complex financial and tax regulations. General-purpose large language models (LLMs) can make such knowledge more accessible, but they often produce fluent yet unsourced or hallucinated answers, which is unacceptable in a financial and regulatory context. This study designs and evaluates IndoRAG-FA, a hybrid Retrieval-Augmented Generation (RAG) framework with explicit hallucination mitigation for Bahasa Indonesia MSME financial advisory. The framework integrates coherence-based semantic chunking; hybrid retrieval combining lexical BM25 and dense multilingual embeddings fused through reciprocal rank fusion; cross-encoder re-ranking; and grounded generation that produces source-cited answers with a confidence-based abstention mechanism and a groundedness verifier. A curated knowledge base was built from authoritative Indonesian financial and tax sources, and an expert-validated benchmark of representative MSME questions, including out-of-scope items, was developed. The framework was compared with an LLM-only baseline and a vanilla RAG baseline using retrieval metrics (Recall@k, MRR, nDCG), faithfulness, answer relevance and correctness, hallucination rate, abstention precision and recall, and a human-expert rubric. Findings indicate that a retrieval-grounded, abstention-aware design offers a practical and trustworthy path toward deployable financial advisory for Indonesian MSMEs and provides a reusable evaluation protocol for domain-specific LLM systems.
Co-Authors Lutfi Mualiman Meritorious Autonomous Rafi Farizki Rafi Farizki Rani Santika Vo Hung Cuong Wicaksono, Freddy