massafolio.dev
About This Engineer

Massa Coulibaly

Full-stack engineer. I build software that works in places where most tools don't reach.

Ex Co-founder & CTO of Afya — USSD-based EMR for Sub-Saharan Africa. UC Berkeley MIMS. Path toward Forward Deployed Engineering.

School:UC Berkeley MIMS
Prev:CTO @ Afya
Focus:Health IT · FDE
Seeking:FDE · Full-Stack

Projects in Data Science, AI & Web Systems below ↓
This is a page that represent a little bit about me and projects I have worked on. The background symbols are Adinkra — hover them.
Kente (a Ghanaian traditional cloth pattern) is in the background too. Find out more ↗

Data Science & AI

// ML/AI

Billboard Hit Prediction Tool

Built and evaluated four ML models on 3,000+ songs using Spotify, Billboard and YouTube APIs, achieving over 80% accuracy predicting chart success.

stack

PythonScikit-learnSpotify APIBillboard APIYouTube APIPandas

highlights

  • Compared Logistic Regression, Random Forest, XGBoost, and SVM — XGBoost topped 80% accuracy
  • Handled severe class imbalance between charting and non-charting songs via SMOTE
  • Engineered audio features (danceability, valence, tempo) into model-ready inputs across 3 APIs
[ ]

ETF Stock Analysis

Constructed time series models to demonstrate the impact of US Unemployment Rate announcements on QQQ, IWM, and SPY ETF prices.

stack

PythonstatsmodelsARIMAGARCHPandasMatplotlib

highlights

  • Modeled volatility clustering around macro announcements using GARCH
  • Ran event-study analysis isolating pre/post announcement price reactions
  • Aligned non-synchronous financial time series from multiple data sources
[ ]

UN Speeches Analysis

Natural language processing analysis of United Nations speeches, extracting patterns, themes and insights from global diplomatic discourse.

stack

PythonspaCyNLTKLDAGensimMatplotlib

highlights

  • Applied LDA topic modeling across decades of multilingual UN speech data
  • Tracked how geopolitical themes shifted over time by country and region
  • Cleaned and normalized noisy OCR-extracted text from scanned UN documents
[ ]

Web Dev & Systems

// INFRA

mibegnon-project

Full-stack scholarship platform with authentication, user dashboard, and automated scholarship scraping — built with Next.js, TypeScript, and Prisma.

stack

Next.jsTypeScriptPrismaPythonJupyter

highlights

  • Built role-based auth with protected dashboard and public-facing routes
  • Automated scholarship discovery via a Python scraper feeding into a Prisma-backed database
  • Designed schema to track scholarship deadlines, eligibility, and user applications
[ ]

Joke Generator

A front-end React app that fetches random jokes from an external API and displays them in a fun, responsive interface.

stack

ReactCSSJoke API

highlights

  • Integrated an external Joke API with live fetching on button click
  • Built with modular, reusable React components
  • Fully responsive layout that adapts across device sizes
[ ]

HIMS — Friends Eye Center

Built a Healthcare Information Management System for a clinic in Ghana, doubling revenue through full process digitalization.

stack

Full-Stack WebDatabase DesignGhana 🇬🇭

highlights

  • Replaced entirely paper-based workflows — patient records, billing, appointments
  • Reduced billing errors and patient wait times significantly post-deployment
  • Worked directly with clinic staff to iteratively design a system fitting their real constraints
[ ]
massa@portfolio:~$ whoami
> Massa Coulibaly — Full-Stack Engineer
> Ex CTO @ Afya · UC Berkeley MIMS '25
> Built software for clinics in Ghana, ML tools for music, and more
> Status: open · targeting FDE / Full-Stack roles
> Contact: massacoulibaly@berkeley.edu
>