Welcome to Yusuf Kiwanuka's Profile
Statistician · Data Analyst · Data Scientist
Ms Statistics Graduate with hands-on experience in Data Engineering and Machine learning : Skilled in Data cleaning, Transformation, Pipeline development, and Statistical modeling.
Google APIs · Tableau REST API · Cron Jobs
Built an automated data pipeline for real-time ingestion and scheduled report distribution. Connecting to the Amazon Redshift PostgreSQL database eliminated manual work and kept stakeholders’ dashboards up to date.
Inventory visibility · Forecasting · 4 countries
Led development and training for a stock ops dashboard providing real-time inventory and stock-out forecasting, enabling proactive supply chain decisions across Kenya , Mozambique , Zambia and Uganda.
Credit metrics · Intake pipeline · ISO-style documentation
As the lead analyst for a new business-loan product, I defined core risk & performance metrics, designed the end-to-end intake pipeline (Application → Credit → Collections), and established weekly KPI reviews with revenue/profit forecasting to guide rollout decisions.
AWS EC2 · Docker · REST API
End-to-end NLP system analyzing comments to rate videos using sentiment and hateful content detection; results exposed via API and dashboard.
Real-time classification · Geolocation
Pipeline to classify and geolocate tweets, surfacing potential hotspots and visualizing them on a dashboard for early warning.
Feature engineering · Model explainability
Built interpretable models to predict corporate bankruptcy using economic and risk indicators. Employed PCA for data exploration and logistic regression to identify key drivers of financial distress
Lightweight static site · Preprocessed visuals
A lightweight, image-first site that explores mortgage loans associated with FHLB banks. It highlights where lending goes across income tiers, risk levels, and community diversity—helping assess alignment with affordable-housing and community-development goals.
R · Clustering methods · Survey statistics
Worked with my professor in developing new clustering methods for SAE — simulations show faster processing and lower RMSE.
Python, R, SQL, NoSQL, AWS, Tableau, MongoDB, Docker
ML: Scikit-learn, TensorFlow, PyTorch , NLP techniques , Hugging Face
ETL &, EDA/Visualization, Time series, Statistical modeling, Predictive Analytics
Git, Linux Cron Jobs, Model Evaluation, API Usage
Masters of Statistics : 2024 – 2026 • GPA 3.95
Bachelor's Degree in Statistics : 2013 – 2017
Email: kiwanuka11@gmail.com
Phone: (619) 764-2262