Skip to content
View abeeraz379's full-sized avatar
🏠
Working from home
🏠
Working from home
1 follower · 0 following

Block or report abeeraz379

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
abeeraz379/README.md

Hi, I'm ABeer Al-Zebda 🐨

Machine Learning Engineer & Data Scientist based in Gaza 🇵🇸

I build end-to-end ML pipelines — from messy raw data to evaluated, documented models. My focus is on making predictions that are accurate enough to actually matter in the real world: healthcare, agriculture, retail, automotive.

🛠 What I work with Python Pandas NumPy Scikit-learn XGBoost CatBoost LightGBM TensorFlow Matplotlib Seaborn SQL Power BI

📌 Recent Projects

  • 🌱 Irrigation Need Classifier — 7-model benchmark on 630K samples → 92.1% accuracy (CatBoost)
  • 💎 Diamond Price Predictor — 97.5% variance explained on unseen data
  • ❤️ Heart Disease Classifier — 87% recall, minimising missed diagnoses
  • 🛒 Retail Sales Forecasting — Random Forest pipeline with GridSearchCV tuning
  • 🚗 Auto MPG Model Benchmark — custom scoring system across 7 regressors

🎓 B.Sc. Computer System Engineering — Al-Azhar University | CGPA 90.3 📜 DeepLearning.AI · Coursera Data Analysis · Gaza Sky Geeks

💻 Tech Stack:

Python SQLite Matplotlib NumPy Pandas scikit-learn TensorFlow Power Bi

📊 GitHub Stats:



Pinned Loading

  1. Arabic-Handwritten-Digits-Dataset Arabic-Handwritten-Digits-Dataset Public

    The MADBase is modified Arabic handwritten digits database contains 60,000 training images, and 10,000 test images. MADBase were written by 700 writers. Each writer wrote each digit (from 0 -9) ten…

    Jupyter Notebook

  2. california_housing california_housing Public

    The goal of this project is to build a machine learning model using a Neural Network to predict housing prices in California based on several input features such as location, income, and housing ch…

    Jupyter Notebook

  3. Prediction-of-Product-sales Prediction-of-Product-sales Public

    This project analyzes the Big Mart Sales dataset through a full data science pipeline: data cleaning, exploratory data analysis (EDA), and predictive modeling. The goal is to uncover patterns in pr…

    Jupyter Notebook 1

  4. Predicting-Irrigation-Need Predicting-Irrigation-Need Public

    A supervised machine learning project that predicts irrigation needs using multi-class classification techniques. The model is trained on a synthetic dataset (630,000 samples) generated from a deep…

    Jupyter Notebook

  5. Bank-Marketing-prediction Bank-Marketing-prediction Public

    The data is related with direct marketing campaigns of a Portuguese banking institution. The marketing campaigns were based on phone calls. Often, more than one contact to the same client was requi…

    Jupyter Notebook 1

  6. Bike-share-rental-feature-engineering- Bike-share-rental-feature-engineering- Public

    This project predicts bike rental demand using the BikeShare_train dataset. I compare regression model (Linear Regression) with and without feature engineering. After engineering time-based, weathe…

    Jupyter Notebook