Hello, I'm
A Data Scientist turns uncertainty into insight.
Transforming complex AI concepts into practical solutions. Specializing in NLP, Computer Vision, and Cloud AI Engineering.
I'm Dania Farooq, a passionate Data Scientist focused on building reliable, user‑centric intelligent systems.
I specialize in model development, experimentation, and deploying AI/ML systems to the cloud. I enjoy turning complex problems into simple, scalable solutions.
This Heart Disease Prediction web app—built with a Flask backend and a Bootstrap frontend—lets users enter key health metrics (age, gender, cholesterol, blood pressure, etc.) and returns risk predictions using multiple ML models (Logistic Regression, Decision Tree, KNN, Naive Bayes, and an ANN). It combines clean, user-friendly UI with robust model inference (Scikit-learn / TensorFlow), supports CSV/SQLite data handling, and is production-ready for cloud deployment with Gunicorn on platforms like Heroku or Streamlit. The backend is powered by Flask, which handles user requests, model inference, and data processing.
A deep learning project that leverages Convolutional Neural Networks (CNNs) to classify skin lesions as benign or malignant from dermoscopic images. Built with TensorFlow/Keras, it supports training, prediction, and optional deployment with Flask for real-time detection, assisting in early diagnosis of skin cancer. The model is developed using TensorFlow/Keras and trained on publicly available datasets such as the ISIC Skin Cancer Dataset, which contains thousands of labeled dermoscopic images. The pipeline involves image preprocessing (resizing, normalization, and augmentation) to improve model generalization.
A full-stack Learning Management System built using Flask (Python) and MySQL, designed to manage courses, students, and instructors efficiently. It provides features like user authentication, course enrollment, content management, and database-driven storage, making it a reliable solution for modern e-learning platforms. Key features include user authentication and role-based access control (admin, instructor, student), course enrollment and progress tracking, assignment management, and content storage with MySQL for persistent, structured data handling. The system also ensures secure login, session handling, and input validation for data integrity.
A machine learning application using Logistic Regression to predict cardiovascular disease from clinical features. Achieved 88% accuracy and deployed with a Flask-based GUI for real-time predictions.The application is deployed with a Flask-based graphical user interface (GUI), allowing users to input health parameters and receive instant predictions on whether they are at risk. The system emphasizes usability, enabling real-time decision support for both patients and healthcare professionals.
AI-Models-2025 is a collection of notebook experiments showcasing different AI / ML model architectures and workflows for 2025. Each notebook demonstrates training, evaluation, and comparison of models using sample datasets, helping users learn best practices in model design, hyperparameter tuning, and performance analysis. The project is ideal for anyone exploring AI model prototyping, experimenting with different architectures, or building a foundation for more advanced machine learning systems.
This Responsive Portfolio project is a modern, mobile-first website template crafted using semantic HTML, responsive CSS (Flexbox/Grid and media queries), and lightweight JavaScript for interactivity. It includes sections for an about blurb, project gallery (with filtering or modals), a skills/tech stack area, a blog or notes section, and a contact form (can be wired to email or serverless endpoints). The layout adapts smoothly to any screen size and emphasizes accessibility, fast load times, and easy customization — perfect for developers, designers, and students who want a professional online presence.