Skip to content
View moized's full-sized avatar

Highlights

  • Pro

Block or report moized

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
moized/README.md

Mohammed Izedin Mohammed

Applied AI · Machine Learning · Data Science. M.Sc. student in Data Science & Big Data at Yıldız Technical University; B.Sc. in Physics Engineering, ranked 1st in my department.

I like problems where careful measurement decides what works: fine-tuning and evaluating speech recognition, retrieval systems with clear evidence, and statistical modelling.

Featured work

Project What it does Stack
Turkish speech recognition (Veribase internship) Fine-tuned Whisper on call-center audio: 50.18% → 25.09% Micro-WER on a locked test set PyTorch, Hugging Face, faster-whisper, Gradio
AI Research Assistant RAG assistant with source-cited answers, calculator and date tools, and an evaluation benchmark FastAPI, Qdrant, SQLite, Gemini API, Streamlit
LearnOS Turns PDFs, notes and videos into study plans for AI tutors; LLM-free topic segmentation FastAPI, SQLite, NumPy, React
Grid load forecasting STL + SARIMAX with stationarity and residual diagnostics statsmodels
Flight anomaly detection PySpark + DBSCAN on OpenSky ADS-B data, Mahalanobis validation PySpark, scikit-learn
Variational autoencoder VAE theory, optimisation and implementation PyTorch

Also: customer segmentation (RFM + K-Means), a feature selection framework, and ICP plasma simulation in COMSOL Multiphysics.

Skills

  • Programming and data: Python, SQL, pandas, NumPy, PySpark, SQLite, Git
  • Machine learning: PyTorch, Hugging Face Transformers, Whisper (ASR), scikit-learn, statsmodels, time-series forecasting, clustering, evaluation (WER, CER)
  • LLMs and retrieval: RAG, embeddings, hybrid BM25 + dense retrieval, Qdrant, Gemini API
  • APIs and apps: FastAPI, REST APIs, Streamlit, Gradio
  • Scientific computing: COMSOL Multiphysics, MATLAB, finite-element modelling

Education and certification

  • M.Sc. Data Science & Big Data: Yıldız Technical University (2025 – present)
  • B.Sc. Physics Engineering: Istanbul Medeniyet University (2020 – 2024), GPA 3.82/4.00, ranked 1st in department, Türkiye Scholarships recipient
  • Data Scientist Associate: DataCamp, Jun 2026 (credential DSA0017995373375)

Contact

LinkedIn · mohammedizedin@gmail.com

Languages: Amharic (native), English and Turkish (fluent).

Popular repositories Loading

  1. IBM-Capstone-Project-Emerging-Skills-Analysis IBM-Capstone-Project-Emerging-Skills-Analysis Public

    A comprehensive analysis of emerging programming and database skills for a global IT and business consulting firm. This project aimed to identify the top in-demand technical skills by analyzing dat…

    Jupyter Notebook

  2. web-scraping-sold-houses web-scraping-sold-houses Public

    Jupyter Notebook

  3. Youtube-API Youtube-API Public

    Jupyter Notebook

  4. Agent-data-collector Agent-data-collector Public

    Jupyter Notebook

  5. Investigating-Netflix-Movies Investigating-Netflix-Movies Public

    Jupyter Notebook

  6. Big-data-project Big-data-project Public

    Distributed flight anomaly detection on OpenSky ADS-B data with PySpark and DBSCAN.

    Jupyter Notebook