Data · AI · Jakarta, Indonesia

Muhammad
Ali

Data Analyst ML Engineer LLM Builder

Building intelligent systems end-to-end — from raw data and machine learning pipelines to AI-powered applications backed by real government deployment experience.

About

Data to decisions,
models to products.

Fresh graduate in Sharia Economics from UIN Syarif Hidayatullah Jakarta (GPA 3.40), combining quantitative foundations with hands-on AI and data engineering experience.

Currently working as Data Analyst at BPPK Kementerian Keuangan — building automation systems, dashboards, and an AI-powered budgeting assistant used in live government financial workflows.

Thesis applied Geographically Weighted Poisson Regression (GWPR) across Indonesian provinces, bridging academic econometrics with production data tools.

Every project approached end-to-end: from ingestion and feature engineering to modeling and user-facing interfaces. Not just analysis — systems that work.

9
Dicoding Certs
282+
Hours of Learning
300+
Employees Tracked
100k+
Orders Analyzed

Projects

What I've built.

01
LLM Application

Arin — AI Budget Analysis Assistant

Arin AI Budget Assistant

AI-powered government budgeting assistant built with Streamlit and Gemini API. Retrieves financial data from 8 Excel sheets, performs automated SBM calculations, and generates structured budget tables. Deployed and actively used for internal financial workflows at BPPK Kemenkeu.

Production · Deployed Gemini APIStreamlit Prompt EngineeringPandas
02
Data Analytics

E-Commerce Customer & Sales Analytics

E-commerce Analytics Dashboard

End-to-end analytics pipeline on 100k+ orders across 9 datasets. Includes data wrangling, feature engineering, RFM customer segmentation, revenue trend analysis, and geospatial mapping — delivered through an interactive multi-tab Streamlit dashboard.

Python · PandasStreamlit RFM SegmentationGeospatial100k+ Orders
03
Dashboard · Production

Employee Travel Activity Dashboard

Excel Employee Dashboard

Interactive Excel dashboard with PivotTables and slicers to monitor 300+ official travel assignments across 94 employees over a 2-month period. Used in production at BPPK Kemenkeu to support structured HR reporting and compliance tracking.

Production · BPPK Kemenkeu Excel AdvancedPivotTables300+ Assignments
04
BI Dashboard

Employee Assignment Analytics — Power BI

Power BI Employee Dashboard

Power BI dashboard built from the same employee travel dataset — visualizing assignment distribution by team, monthly trends, and employee workload. Demonstrates cross-tool fluency: the same data source explored through both Excel and Power BI for different reporting needs.

Power BIData Modeling DAXGovernment Data
05
Machine Learning

Bank Transaction ML Pipeline

Full end-to-end ML pipeline on 2,538 bank transactions — preprocessing, feature engineering, clustering, and classification to identify transaction patterns and surface analytical insights. Built with Scikit-learn from raw data to evaluated model.

Python · Scikit-learn Clustering · Classification Feature EngineeringModel Evaluation
06
Computer Vision

CNN Rock–Paper–Scissors Classifier

Image classification model using TensorFlow and VGG16 transfer learning with data augmentation, callbacks, and ImageDataGenerator pipeline. Achieved over 97% accuracy on the Dicoding dataset — full training pipeline built from scratch.

TensorFlow · KerasVGG16 Transfer Learning 97%+ AccuracyData Augmentation

Skills

Stack & tools.

Machine Learning
  • Python · Scikit-learn
  • TensorFlow · Keras
  • Classification & Clustering
  • Feature Engineering
  • Model Evaluation
  • Computer Vision (CNN)
AI & LLM
  • Gemini API · Google GenAI
  • Prompt Engineering
  • RAG-style Retrieval
  • Ollama · LM Studio
  • LangChain · Dify
  • AI App Development
Data & Analytics
  • Pandas · NumPy
  • Excel Advanced · Power BI
  • Tableau · Streamlit
  • RFM Segmentation
  • Geospatial Analysis
  • Power Automate
Programming & DB
  • Python (primary)
  • R · RStudio
  • SQL · MySQL · SQLite
  • DBeaver
  • Git · GitHub
Domain Knowledge
  • Government Financial Systems
  • SAKTI · Budget Automation
  • Sharia Economics
  • Spatial Econometrics
  • Financial Data Validation
Currently Building
  • FastAPI · REST API
  • Docker
  • MLflow · Model Monitoring
  • Azure AI Foundry · RAG
  • Microsoft Fabric

Experience

Where I've worked.

Dec 2025 — Present
BPPK · Kemenkeu RI

Data Analyst

  • Analyzed and validated financial expenditure data — travel, transport, allowances — to ensure accuracy and compliance in government budgeting processes
  • Developed interactive Excel dashboards to monitor 300+ assignments across 94 employees, supporting data-driven decision-making
  • Automated financial data workflows using Power Automate to streamline SAKTI integration and reduce manual processing
  • Built Arin, an AI assistant using Streamlit and Gemini API for automated budget validation and financial calculations from live Excel data
ExcelPower Automate SAKTIStreamlit · Gemini API

Education

Academic background.

Sep 2021 — Jul 2025
UIN Syarif Hidayatullah Jakarta

S1 Ekonomi Syariah

GPA 3.40 / 4.00

Thesis: GWPR Analysis of Internet Access, Education, Labor Force, and Sharia Financing Across Indonesian Provinces — applied Geographically Weighted Poisson Regression using R, GWmodel, spdep, and GeoDa to analyze spatial heterogeneity across 34 provinces.

R · RStudioGWmodel · spdep GeoDaSpatial Econometrics

Certifications

282+ hours of structured learning.

Belajar Fundamental Analisis Data
Dicoding · 70 jam · Menengah
Belajar Machine Learning untuk Pemula
Dicoding · 90 jam · Pemula
Memulai Pemrograman dengan Python
Dicoding · 60 jam · Dasar
Membangun Aplikasi Gen AI dengan Microsoft Azure
Dicoding · 8 jam · Menengah
Belajar Penerapan Data Science dengan Microsoft Fabric
Dicoding · 6 jam · Pemula
Belajar Dasar Visualisasi Data
Dicoding · 16 jam · Dasar
Belajar Dasar AI
Dicoding · 10 jam · Dasar
Belajar Dasar Data Science
Dicoding · 11 jam · Dasar
Belajar Dasar SQL
Dicoding · 11 jam · Dasar

Let's work together.

Open to roles in AI, data, and Machine Learning. Reach out via LinkedIn, GitHub, Or Email.