Data Science · Dashboards · Systems

Finding the signal in the noise.

Each star in orbit is a project. Pick a skill to light up the projects built with it.

  • Data Science
  • Dashboards
  • Systems
AeroCSystems · 2025
Eskwelabs Event Performance DashboardDashboards · 2026
AWS ETL DashboardDashboards · 2026
Data 001: Synthetic Data Under Data ScarcityData Science · 2026
Data 002: Synthetic Restoration Controls under Data ScarcityData Science · 2026
Tawad: Palengke Price TrackerSystems · 2026
StargazeSystems · 2026

KG Star System7 projects in orbit · 3 practices

About

I work across data analytics, AI engineering and cloud development. Across two internships I have built automated dashboards, Python data pipelines, backend services and cloud-deployed models, and I validate them on held-out data and with real users.

I'm studying BS Information Technology at the Polytechnic University of the Philippines (expected June 2028, GPA 1.42) and lead the Data Science and Analytics Department of the AWS Student Builder Group PUP Manila.

internship
1
workshops taught
5+
members reached
300+
Hackathon wins
2x
  • SystemsKG-0007 · 2026

    Stargaze

    A star, galaxy, and quasar classifier built on five brightness measurements that stays accurate on noisy or incomplete data and says “not sure” when it can’t be trusted.

    • Python
    • uv
    • pytest
    • +9
  • SystemsKG-0006 · 2026

    Tawad: Palengke Price Tracker

    A daily-updated, open-data pipeline that turns ~2,900 Department of Agriculture price-report PDFs into a clean table of ~890,000 Metro Manila palengke prices, published as a BigQuery dataset and Looker Studio dashboard.

    • Python
    • uv
    • pytest
    • +7
  • Data ScienceKG-0005 · 2026

    Data 002: Synthetic Restoration Controls under Data Scarcity

    A matched-control follow-up to Data 001 that tests whether Gaussian Copula augmentation beats simply duplicating scarce real rows. It never did, and it was practically harmful in 10 of 18 settings.

    • Python
    • pytest
    • GitHub Actions
    • +2
  • Data ScienceKG-0004 · 2026

    Data 001: Synthetic Data Under Data Scarcity

    A benchmark testing whether Gaussian Copula synthetic data can make up for scarce real healthcare training data. It couldn’t: augmentation helped 0 of 18 conditions and hurt 14.

    • Python
    • Jupyter Notebook
    • pytest
    • +3
  • DashboardsKG-0003 · 2026

    AWS ETL Dashboard

    Built an automated, cloud-native weather data pipeline on AWS (EC2, Lambda, EventBridge) that loads curated data into Redshift for a Looker Studio dashboard, and taught the build to 40+ members in a hands-on workshop.

    • AWS EC2
    • AWS Lambda
    • AWS EventBridge
    • +2
  • DashboardsKG-0002 · 2026

    Eskwelabs Event Performance Dashboard

    An automated Looker Studio dashboard that brought four years of event data (80+ events, 1,000+ attendees) into one view.

    • Looker Studio
    • Google Sheets
    • SQL
  • SystemsKG-0001 · 2025

    AeroC

    An air pollution exposure simulator that won 1st place out of 25 teams at the Solar Power Hackathon.

    • Python
    • FastAPI
    • AWS EC2
    • +1
Hosted

From Raw Data to Cloud Insights

Built a cloud data pipeline with members, from S3 through Lambda, EventBridge and Redshift to Looker Studio, then taught how to design dashboards people can read at a glance.

Attended

PyTorch Philippines Community Meetup

Learned how data science is done in practice from data scientists at EY GDS, the Asian Development Bank and Smart Communications at the launch of the PyTorch Philippines community.

AWS Office, BGC, Taguig

Hosted

Data Manipulation in Pandas

Taught students to handle data with pandas, Python's go-to library for tables, from importing CSV files to merging datasets.

Attended

State of the Nation in AI

Attended SONAI 2026, the Global AI Council Philippines' yearly summit on where AI stands in the country, and heard lawmakers lay out plans for AI policy.

GSIS Building, Pasay City

Volunteered

Hour of AI 2025

Helped elementary students understand how AI works, using simple ideas like how a computer tells cats from dogs by their features.

Attended

AWS Technology Department Kickoff 2025

Started my term as Co-Lead of the Data Science and Analytics Department, met my fellow leads, and learned the 5 buckets of knowledge we use to plan our teaching.

Attended

Solar Power Hackathon 2025

Led the backend team for AeroC, an air pollution exposure simulator that placed 1st out of 25 teams.

More events coming