Data Science + ML Engineering

Applied AI systems from data to deployment.

I design machine learning products, analytics pipelines, and decision-support tools for teams that need models to be useful, explainable, and production-ready.

Addis Ababa, EthiopiaCredit risk, fraud, forecasting, and computer vision.
I'm a data scientist with a background in Python programming. I enjoy figuring out how things work whether it's good coding practices, engineering techniques, or machine learning methods. My work mainly involves building machine learning applications, analyzing data, and creating visualizations to uncover insights. I'm a firm believer in open-source collaboration, as I see shared solutions as a way to drive innovation within the community. Python is my go-to tool for daily work, helping me develop efficient and scalable solutions. I find purpose in using data to address global challenges such as climate change, poverty, healthcare, governance, and sustainable development. I aim to contribute to meaningful change by developing solutions that connect technology with human progress. Beyond data science, I'm deeply interested in endurance sports and healthy living. You can find my work on my website, including GitHub code, professional reports, and interactive visualizations. Thanks for visiting I hope you find something inspiring!Clinton
Explore ProjectsRead Technical Notes
ALX Africa | Data Science
10 Academy | AI Mastery
Addis Ababa University (2019-2024) | BSc in CoTM
Clinton Beyene standing portrait

Profile

Data scientist + ML engineer

Data scientist in Addis Ababa building applied ML systems, dashboards, and decision-support tools.

Selected Work

Featured projects

View all projects
CubeSat Image Classification project preview
Computer Vision
PythonFastAPIComputer VisionAWSTensorFlow+4
Computer Vision

CubeSat Image Classification

Compressed satellite image classification workflow for edge-ready decision support.

A lightweight machine learning pipeline designed for CubeSat image classification, optimizing data transmission efficiency in space. This project integrates preprocessing, model training, pruning, quantization, and evaluation to enable real-time decision-making onboard resource-constrained satellites. Inspired by the VERTECS mission, it ensures high accuracy while minimizing computational costs.

PythonFastAPIComputer VisionAWSTensorFlow+4
Credit Scoring Model project preview
Financial AI
PythonScikit-learnSHAPStreamlit
Financial AI

Credit Scoring Model

Explainable credit-risk scoring pipeline for BNPL lending decisions.

A machine learning model developed to predict credit risk and assign credit scores, supporting data-driven lending decisions for Bati Bank's Buy-Now-Pay-Later (BNPL) service in collaboration with an eCommerce platform.

PythonScikit-learnSHAPStreamlit

Financial AI

Applied model pipeline

PythonMLflowSHAPStreamlitDocker
Financial AI

Fraud Detection Pipeline

Fraud detection workflow with explainability, deployment, and dashboard-ready outputs.

This project leverages machine learning to detect fraudulent transactions in e-commerce and banking, aiding in proactive security and risk management. The goal is to provide a robust fraud detection pipeline with explainability, deployment, and dashboard visualization for actionable insights.

PythonMLflowSHAPStreamlitDocker
Portfolio Forecasting project preview
Forecasting
PythonPandasTensorFlowKeras
Forecasting

Portfolio Forecasting

Time-series forecasting workflow for asset allocation and portfolio risk management.

This project uses advanced time series forecasting models to enhance portfolio management for Guide Me in Finance (GMF) Investments. By analyzing historical data for Tesla (TSLA), Vanguard Total Bond Market ETF (BND), and S&P 500 ETF (SPY), we aim to forecast market trends, optimize asset allocation, and manage risk.

PythonPandasTensorFlowKeras

Writing

Latest notes

Read more