Hi, I'm

Martin Ngoh

|

    • ABOUT

    Senior Data Scientist with 4+ years developing, deploying, and delivering AI that leverages data for business growth.

    4+ Years Experience
    2 Degrees
    10+ Projects
    5+ Models Deployed
    2021 — Present

    Data Scientist

    Building AI solutions that drive business growth for clients across industries.

    2022

    M.S. Business Analytics

    Georgetown University

    2020

    B.S. Supply Chain Management & Analytics

    Virginia Commonwealth University

    Skills

    Python PySpark SQL Git HTML R SAS JavaScript CSS
    AWS Azure Tableau TensorFlow PyTorch MLFlow LangChain NumPy Pandas Matplotlib Seaborn Sklearn Hugging Face Prophet OpenAI Claude API XGBoost RAG Vector Search Embeddings

    PROJECTS

    AI products and data solutions

    Resume Bot

    Built an app that matches resumes to job descriptions through LLMs and transformers. Uses cosine similarity for matching and assessment.

    Python Jupyter
    LLM Embeddings Transformers Cosine Similarity

    live

    Soccer Prediction Model (SPM)

    Player-level goals prediction model built on 2,786 players across 104 countries. Tested 8 models with full GridSearch tuning — best was Linear Regression with R²=0.680 and RMSE=0.249 on the test set.

    Python SQL Jupyter
    Linear Regression CatBoost LightGBM Random Forest Neural Network

    DC Lease Helper

    A deployed RAG app that reads your DC lease, compares it against the DC Tenant Bill of Rights, and lets you ask plain-language questions about your lease.

    Python Claude API Railway
    RAG Vector Search LLM

    live

    Champions League 2024

    Scraped web data using Python to analyze Champions League goal-scoring trends from 2008–2024. Best model was XGBoost with 0.647 training RMSE and 0.854 on unseen 2023–24 season data.

    Python Jupyter
    XGBoost Web Scraping Data Visualization
    More on GitHub →