Skip to content
View pngo1997's full-sized avatar

Block or report pngo1997

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pngo1997/README.md

Hi there πŸ‘‹

I’m Mai Ngo, a passionate Data Scientist with a strong foundation in machine learning, NLP, data visualization, and big data processing. I truly believe that data can drive impactful business decisions and foster societal growth. My goal is to extract meaningful insights, develop scalable models, and create data-driven solutions that make a difference.

πŸŽ“ Education

  • Master’s in Data Science (Computational Methods) | DePaul University.
  • Bachelor’s in International Business, Finance, and Economics | University of Wisconsin-Superior.

πŸš€ About Me

  • πŸ“Š Expertise in: Data Science & Statistical Analysis, Machine Learning, Recommender Systems, NLP, Deep Learning (RNN, LSTMs, Transformers), Data Mining & Visualization, Cloud Computing (AWS, Hadoop), and Power BI/Tableau.
  • πŸ“Œ Industry Experience: Data Science & Statistical Analysis, Data Mining & Visualization, Data Warehouse, Business Intelligence, Recommender Systems, Natural Language Processing, Machine Learning Models, Deep Learning, Programming, Compliance, Project Management, Customer Service, Supervision.

πŸ›  Technical Skills

  • πŸš€ Machine Learning & AI: TensorFlow PyTorch Scikit-Learn Keras Hugging Face
  • πŸ“Š Data Analytics & Visualization: Pandas NumPy Power BI Tableau
  • πŸ’Ύ Databases & Cloud: AWS Hadoop SAP S/4HANA SQL
  • πŸ›  Programming Languages: R Python SQL SAS
  • πŸ“‚ Other Tools: Jupyter Notebook Salesforce Microsoft Office

πŸ”Ž Key Projects

  • 🏑 Semantic-driven Hybrid Recommender System for Chicago Airbnb Listings – Built a system leveraging embeddings, sentiment analysis, and proximity to train stations to enhance Airbnb recommendations.
  • 🍽️ Item-based Collaborative Recommender for Yelp Establishments – Developed collaborative filtering models to recommend establishments based on shared characteristics.
  • πŸ“ˆ Financial Data Analysis – Power BI Framework for Underwriting Analytics – Built a custom reporting and analysis framework in Power BI to analyze AXA underwriting performance.
  • πŸ“° Fake News Detection – Designed an NLP-based misinformation classification model using TF-IDF and LSTMs.
  • πŸ€– Building N-gram Language Models & Retrieval Augmented Generation (RAG) – Trained Mistral 7B & GPT-3.5 Turbo to evaluate perplexity and retrieval efficiency.

🌱 What I’m Working On

  • Business analytics framework and data warehouse.
  • Expanding my expertise in LLMs (Mistral, T5), Vector Search, and RAG.
  • Exploring MLOps, Databricks, and scalable ML deployment.
  • Actively seeking new opportunities in Data Science & AI

πŸ“« Connect with Me

Looking forward to connect with you! ⚑

Popular repositories Loading

  1. Astrophysical-Object-Classification Astrophysical-Object-Classification Public

    Astrophysical Object Classification using a hybrid static and time series data.

    Jupyter Notebook 1

  2. Grading-Logic Grading-Logic Public

    Grading logic system to evaluate student assignments based on specific criteria.

    HTML

  3. Coprime-Checker Coprime-Checker Public

    Determines whether two integers are coprime.

    Jupyter Notebook

  4. Stem-Leaf-Plot Stem-Leaf-Plot Public

    Generates Stem-and-Leaf Plots from numerical data files.

    Jupyter Notebook

  5. Goldbach-Project Goldbach-Project Public

    Verifies Goldbach's Conjecture - prints two primes sum up to an even integer (less than 100).

    Jupyter Notebook

  6. Prime-Moods Prime-Moods Public

    Determines whether an integer is a happy prime, sad prime, happy non-prime, or sad non-prime based on given criteria.

    Jupyter Notebook