Skip to content
View elfahad98's full-sized avatar
3 followers · 2 following

Achievements

Achievement: Galaxy Brainx2Achievement: Pull SharkAchievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Galaxy Brainx2Achievement: Pull SharkAchievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report elfahad98

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
elfahad98/README.md

El-Fahad COMBO — Data Science / Machine Learning

MSc Applied Mathematics & Statistics (Data Science) — Université de Caen Normandie 🇫🇷

I build end-to-end ML projects (data → features → model → evaluation) with clean, reproducible pipelines.
🎯 Seeking Data Science / Machine Learning internship (Feb–Aug 2026)

Open to: Data Science • Machine Learning • Data Engineering (ETL) • Analytics • Cloud (Azure)

🧠 About

  • 📌 Focus: Fraud detection, imbalanced classification, feature engineering, model evaluation
  • 🧱 Also: ETL / datawarehouse (star schema), SQL, data quality checks
  • ☁️ Cloud: Azure ML (DP-100 prep), experiments, pipelines, MLOps fundamentals

🧰 Tech Stack (clean & modern)

🔥 Featured Projects

🏦 Fraud Detection — IEEE-CIS (Kaggle)

Tech: PySpark • Spark MLlib • Python • SQL • (Optional) Superset
What I did:

  • Distributed pipeline: load + join identity, cleaning, missing values handling
  • EDA: isFraud distribution, key drivers, first engineered features
  • Supervised modeling + metrics tracking (AUC, precision, recall)

➡️ Repo: https://github.com/elfahad98/ieee-fraud-pyspark

🔐 Account Takeover (ATO) Detection

Tech: Python • scikit-learn • XGBoost • Pandas • NumPy
What I did:

  • Behavioral features (time patterns, frequency, device signals, etc.)
  • Imbalanced learning + benchmarking + thresholding with low false positives in mind

➡️ Repo: https://github.com/elfahad98/ato-fraud-detection-mlp

🏗️ ETL & Datawarehouse (Mobility / Sales)

Tech: Apache Hop • PostgreSQL • SQL
What I did:

  • Star schema design (fact + dimensions)
  • ETL workflows: ingestion, cleaning, quality checks, error handling
  • (Concepts) Slowly Changing Dimensions (SCD2)

➡️ Repo: https://github.com/elfahad98/etl-datawarehouse

📫 Contact

Pinned Loading

  1. ieee-fraud-pyspark ieee-fraud-pyspark Public

    Détection de fraude bancaire avec PySpark — pipeline ML distribué

    Jupyter Notebook 4

  2. ato-fraud-detection-mlp ato-fraud-detection-mlp Public

    Analyse et modélisation d’un système de détection de fraude (Account Takeover) pour repérer les connexions suspectes et comportements anormaux.

    Jupyter Notebook 4

  3. base-donnees-foot base-donnees-foot Public

    Application web en PHP + PostgreSQL pour gérer une base de joueurs de football.

    HTML 1

  4. game-trio game-trio Public

    Application Python (Tkinter) regroupant trois jeux interactifs : Snake, Turmites et Conway’s Game of Life.

    Python 1

  5. etl-datawarehouse etl-datawarehouse Public

    Mini Data Warehouse alimenté via des pipelines ETL Apache Hop (dimensions + fait). Modélisation étoile, SQL, et gestion de la qualité des données.

    1