Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal TEPIAN
Karjadi, Markus
Unknown Affiliation
Computer Science & IT

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

Found 2 Documents
Search

 1 
Comparative Evaluation of Large Language Models for Intent Classification in Indonesian Text Karjadi, Markus; Santoso, Handri
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3355

Abstract

Large Language Models (LLMs) have shown tremendous potential in intent classification tasks, yet their practical deployment in low-resource language environments remains underexplored. This study presents an informatics-based evaluation framework to compare three LLM architectures—GPT-Neo (fine-tuned), Mistral, and Phi-2.0 (zero-shot inference)—on Indonesian intent classification. The methodology integrates classic informatics approaches such as stratified sampling, label encoding, model evaluation using Scikit-learn, and a REST API-based local inference pipeline via the Ollama framework. The study also benchmarks computational efficiency by profiling execution times on consumer-grade hardware. GPT-Neo achieved 100% accuracy after fine-tuning, while Mistral and Phi-2.0 scored approximately 55% and 18%, respectively, in zero-shot settings. The hybrid architecture designed in this work demonstrates how LLMs can be systematically evaluated and deployed using lightweight, modular informatics workflows. Results suggest that fine-tuned lightweight models are viable for high-accuracy deployment, while zero-shot models enable rapid prototyping under constrained resources.
TOGAF-Based Business Architecture Design for FinLy in Innovation and Monetization of AI-Based Digital Financial Services Karjadi, Markus; Indrajit, Richardus Eko; Dazki, Erick
TEPIAN Vol. 6 No. 3 (2025): September 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i3.3413

Abstract

This study aims to design a business architecture for FinLy, a digital startup focused on the development and monetization of AI-based financial products. The approach follows the TOGAF Architecture Development Method (ADM), with particular emphasis on the Architecture Vision, Business Architecture, and Opportunities & Solutions phases. Employing a Design Science Research methodology, the architectural models are constructed using ArchiMate, Business Model Canvas, and Business Capability Mapping. Findings demonstrate that FinLy’s business architecture effectively maps four core capability domains to ten revenue streams that align with its digital monetization strategy. Evaluation results indicate that the architecture is modular, adaptive, and strategically aligned. The novelty of this research lies in the end-to-end integration of the TOGAF framework, generative AI technologies, and digital monetization mechanisms within the context of financial product design. As such, FinLy serves as a reference model for financial startups seeking to establish a capability-based enterprise architecture supported by cloud-native tools like Figma, Google Cloud Platform, and Oracle Database. This work contributes to the advancement of business architecture frameworks that are both technically efficient and capable of delivering personalized, adaptive, and commercially sustainable services in the digital era
Co-Authors Dazki, Erick Richardus Eko Indrajit Santoso, Handri