Skip to content
Logo
arrow_backHomeBeranda

05.ProjectsProyek

co_present
Web

Lectura — Academic PresentationLive open_in_new

An All-in-One Teaching Stage SPA built with native ES Modules, incorporating a Wiki-Study curriculum mode, a Reveal.js presentation engine with LaTeX/Mermaid integration, and an infinite Canvas whiteboard synced to SQLite.

3 Connected ModesSQLite Sync5-Layer JS & 11-Layer CSS
Stack
Node.jsSQLiteReveal.jsMathJaxMermaid.jsesbuildPostCSS
psychology
Web

Maestro — Intelligent Tutoring SystemLive open_in_new

An Intelligent Tutoring System (ITS) built on Flutter & Cloud Firestore, utilizing a Q-POMDP Reinforcement Learning engine and local Markdown RAG to deliver personalized pedagogical interventions via Groq/Gemini APIs.

Flutter 3.41.7Riverpod 2.6.1HAKI Copyright
Stack
FlutterRiverpodQ-LearningFirebaseCloud FirestoreGroq/Gemini API
description
Academic

Udinus Thesis Template (LaTeX)Repo open_in_new

A production-ready LaTeX thesis template for Udinus with one-command XeLaTeX compilation and arXiv citation integration — adopted by fellow students who were tired of fighting Word formatting.

2 GitHub forks1-command compilationMCP arXiv integration
Stack
LaTeXXeLaTeXBiberArXiv APIMCP
analytics
Academic

Meta Analysis Data MedicRepo open_in_new

ETL pipeline and Network Meta-Analysis (NMA) using R and MetaInsight to analyze antidepressant clinical trials and datasets, backed by Pandas, NumPy, and SQL.

3 clinical trial datasetsETL pipelineMetaInsight NMA
Stack
RPandasNumPySQLMetaInsight
model_training
Project

Machine Learning Modeling & Implementation

Multi-Head Attention architectures for stock market prediction published at ICAMIMIA 2025 (Scopus) — plus LSTM models deployed in production data pipelines for automated time-series forecasting.

ICAMIMIA 2025100+ ablation runsGPU cluster training
Stack
PythonTensorFlowPyTorchLSTMMulti-Head Attention
gavel
Project

JustExplain — Explainable AI Sentencing Predictor

A collaborative XAI research project predicting Indonesian court sentencing lengths using Random Forest + XGBoost with SHAP attribution and a Streamlit dashboard. Lead author: Jarot · Contributor: Praditya (ML pipeline, research design, data preprocessing).

R² 0.81MAE 7.03 mosRMSE 11.87 mos22.6k+ cases
Stack
PythonScikit-LearnXGBoostSHAPMLflowStreamlitGitPythonlxmlPandasNumPySciPyStatsmodelsSeaborn
translate
Project

IndoBERT Fine-Tuning — NLP for Indonesian Language

Fine-tuned IndoBERT for Indonesian language understanding tasks using Hugging Face Transformers — with experiment tracking via MLflow, GPU-accelerated training, and systematic evaluation across text classification and sentiment analysis benchmarks.

+2% F1 over baseline50+ configs trackedLoRA (95% fewer params)
Stack
PythonHugging FaceIndoBERTLoRAMLflowGPU (CUDA)Experiment Tracking
alt_route
Web

API Gateway — Enterprise PatternRepo open_in_new

A zero-framework API Gateway implementing JWT authentication, sliding window rate limiting, and circuit breaker for microservice traffic management — built with native Node.js HTTP module.

Zero-frameworkJWTCircuit Breaker
Stack
Node.jsSQLiteJWTDockerFly.io