I am a final-year Computer Science student specializing in Data Science and Machine Learning. I transform raw data into actionable insights through statistical analysis, supervised and unsupervised learning, and deep learning, building and optimizing ML models through hands-on projects and internships. I am passionate about applying AI to real-world problems and continuously expanding my technical expertise through certifications and collaborative projects.…

Ebrahim Zaher

I am a final-year Computer Science student specializing in Data Science and Machine Learning. I transform raw data into actionable insights through statistical analysis, supervised and unsupervised learning, and deep learning, building and optimizing ML models through hands-on projects and internships. I am passionate about applying AI to real-world problems and continuously expanding my technical expertise through certifications and collaborative projects.…

Available to hire

I am a final-year Computer Science student specializing in Data Science and Machine Learning. I transform raw data into actionable insights through statistical analysis, supervised and unsupervised learning, and deep learning, building and optimizing ML models through hands-on projects and internships.

I am passionate about applying AI to real-world problems and continuously expanding my technical expertise through certifications and collaborative projects.

See more

Language

English
Advanced
Arabic
Fluent
German
Beginner

Work Experience

Machine Learning Intern at National Telecommunication Institute (NTI)
January 1, 2025 - Present
Gained hands-on experience in advanced ML concepts, model optimization, and deployment. Built and evaluated ML models using Python and Scikit-learn. Applied supervised and unsupervised learning techniques to real-world datasets.

Education

B.Sc. in Computer Science at Mansoura University
January 11, 2030 - July 1, 2026

Qualifications

Supervised Learning with scikit-learn – DataCamp
January 11, 2030 - October 15, 2025
Unsupervised Learning with scikit-learn – DataCamp
January 11, 2030 - October 15, 2025
Machine Learning with Tree-Based Models – DataCamp
January 11, 2030 - October 15, 2025
Deep Learning Fundamentals – NVIDIA
January 11, 2030 - October 15, 2025
Natural Language Processing (NLP) – Ongoing Study
January 11, 2030 - October 15, 2025
Convolutional Neural Networks (CNN) – Ongoing Study
January 11, 2030 - October 15, 2025
Linear Algebra, Calculus, Probability & Statistics for Data Science – Self-study
January 11, 2030 - October 15, 2025

Industry Experience

Software & Internet, Education, Telecommunications, Professional Services, Other, Media & Entertainment
    paper Pneumonia Detection
    Here are a few descriptions for your project. You can choose the one that best fits your audience. Option 1: Project Summary (For a Portfolio or LinkedIn) This project is an advanced Chest X-Ray Classifier designed to detect pneumonia. It uses a powerful hybrid approach that combines deep learning for feature extraction with a traditional machine learning model for classification. First, a pre-trained MobileNetV2 model (fine-tuned by unfreezing the top 30 layers) is used as a sophisticated feature extractor. It processes the X-ray images and converts them into high-level numerical feature vectors. These features are then fed into a Support Vector Machine (SVM) with a polynomial kernel, which is trained to distinguish between 'Normal' and 'Pneumonia' images. This two-step process leverages the powerful image-understanding of deep learning and the robust classification power of SVMs. The final trained SVM model and its corresponding class names are saved using joblib and pickle for future use in an application.…
    paper Mobile Reviews Sentiment
    This project is a Sentiment Analysis classifier built to determine the sentiment (Positive, Negative, or Neutral) of mobile phone reviews. The model was trained on a dataset of 50,000 reviews and uses a hybrid feature approach for high accuracy: Textual Data: It analyzes the review text itself using a TF-IDF Vectorizer. Metadata: It also incorporates other structured data, such as the phone's brand, model, price, and the reviewer's star rating. By combining all these features, the final Logistic Regression model achieved 97.7% accuracy on the test data. The complete pipeline, including the trained model, TF-IDF vectorizer, and feature encoder, was saved for future use in a live application.…