Data Science · Machine Learning · AI

Muhammad Aldo Fahrezy

I turn messy, real-world data into measured results — building end-to-end ML pipelines across computer vision, NLP, and tabular modeling, hardened through 15+ data-science competitions.

View selected work Résumé

3.88
GPA · Universitas Indonesia: 15+
ML / DS competitions: R² 0.992
Best-of-9 carbon model: 8.0
IELTS · C2 English

Selected work

Case studies

A few projects worth the depth — each written up with the reasoning behind it, the measured results, and honest limitations.

Interpretable ML

Carbon Footprint Prediction — A Comparative, Interpretable ML Study

Nine regressors benchmarked to predict an individual's carbon emissions from behavior — where disciplined preprocessing turned a middling model into a CatBoost regressor with MAE 66.4 (44% below the runner-up), and SHAP explained why.

CatBoost
LightGBM
XGBoost
SHAP
scikit-learn
Pandas

0.9920R² · CatBoost (best of 9)

Technical report · Universitas Indonesia

View case study

Agentic AI

WarungFlow — Autonomous Finance Ops for Micro-Businesses

An LLM-agent system that reads a warung's WhatsApp-style orders, reconciles them against QRIS and bank transfers with fuzzy name-matching, and reports cashflow and a business-health score — winner of Best Payment Use Case at OpenClaw Agenthon Indonesia 2026.

Python
LLM Agents
Tool Use
DOKU
QRIS
Fintech

🏆Best Payment Use Case · OpenClaw 2026

OpenClaw Agenthon Indonesia 2026 · 🏆 Best Payment Use Case

View case study

Geospatial ML

BanjirWarga — Community Flood Intelligence

A flood-intelligence platform for Indonesian cities: a medallion data pipeline feeding an explainable 0–100 risk score, a report trust score, and a Dijkstra-based safe-route engine over a risk-weighted road graph — served through a PostGIS backend and an offline-capable map PWA.

FastAPI
PostGIS
PostgreSQL
React
TypeScript
Leaflet

0–100Explainable flood-risk score

GEMASTIK PPL 2026

View case study

Distributed Systems

BidMart — Distributed Auction Marketplace

A production-shaped microservices marketplace whose Rust auction engine settles money correctly even when processes crash mid-transaction — via a transactional outbox, a lease-locked job queue, and a two-phase settlement saga.

Rust
axum
gRPC
RabbitMQ
PostgreSQL
Spring Boot

6Bounded-context services

Advanced Programming project · Universitas Indonesia

View case study

See all projects →

About

I’m a Computer Science student at Universitas Indonesia (GPA 3.88), focused on Data Science and Artificial Intelligence. My work spans the full ML lifecycle — from framing a messy problem and cleaning data to benchmarking models, explaining them, and shipping them behind a real interface.

I learn fastest under pressure, which is why I compete: 15+ data-science and ML competitions across computer vision, NLP, and tabular modeling, with wins and finals at the national and international level. Alongside that, I build production systems — from Rust microservices to full-stack, cross-platform apps.

I teach what I learn, too — as a Teaching Assistant I run tutorials for Linear Algebra, Statistics & Probability, and Programming Foundations, grading 200+ students a semester.

Experience

Leading, teaching, competing

Data Science & AI Member

Mar 2026 — present

RISTEK Fasilkom UI

Compete in DSAI competitions in member-formed teams and internal contests; attend weekly training reinforcing ML/DL skills.
Contribute to DSAI research (currently on Retrieval-Augmented Generation).
Assisted in problem-setting for Datathon 2026.

Local Committee Vice President — Outgoing Global Volunteer

Feb 2026 — present

AIESEC in Universitas Indonesia

Lead a department spanning external relations, marketing, customer experience, and international relations.
Manage end-to-end data tracking for the LEADs pipeline.
Coordinate with international partners on UN SDG-aligned programs, generating revenue through exchange products.

Teaching Assistant

Aug 2025 — present

Faculty of Computer Science, Universitas Indonesia

Deliver tutorials for Linear Algebra, Programming Foundations II (Java), Statistics & Probability, and Introduction to Digital Systems.
Coordinate with 4 lecturers and grade 200+ students per semester.

Honors & awards

Recognition

National

Bank Indonesia Scholarship — “Skema Unggulan”

Merit scholarship awardee.

Central Bank of the Republic of Indonesia · 2025

National

Best Payment Use Case — OpenClaw Agenthon Indonesia

WarungFlow — an autonomous multi-agent finance-ops system for Indonesian UMKM.

OpenClaw · 2026

University

2nd Winner — PKM-PI, Olimpiade Ilmiah Mahasiswa (OIM UI)

Full-stack digital ecosystem for AWMI with an NLP chatbot + Human–AI handoff.

BEM Universitas Indonesia · 2025

University

3rd Winner — Pekan RISTEK Data Science Competition

Seismic S-wave arrival-time prediction on the STEAD dataset.

RISTEK Fasilkom UI · 2025

International

Finalist — GarudaHacks 6.0 International Hackathon

Batik pattern recognition with a custom CNN + Gemini API.

GarudaHQ · 2025

National

1st Winner — RISE! IT Business Case Competition

Industry-4.0 solution (ERP + IoT + AI) for PT INALUM.

Institut Teknologi Sepuluh Nopember (ITS) · 2024

Skills

The toolkit

Machine Learning & Data Science

Tabular / Structured Data
Computer Vision
NLP
Feature Engineering
EDA
XAI / SHAP
Ensemble Methods
Time-Series
Model Calibration

ML Libraries & Frameworks

scikit-learn
XGBoost
LightGBM
CatBoost
TensorFlow
PyTorch
MediaPipe
spaCy
NLTK
Pandas
NumPy
Matplotlib
Seaborn

Languages & Engineering

Python
Java (Spring Boot)
Rust
SQL
JavaScript / TypeScript
REST API Design
Docker
Git / GitHub
Linux CLI

Web & Full-Stack

Next.js
React
Django
Node.js
Flutter
WebSockets
PostgreSQL
MongoDB
Prisma ORM

Languages

Certifications

Java Associate (Microsoft)
Intro to Machine Learning (Kaggle)
Deep Learning (Kaggle)
Adobe Certified Professional — Visual Design