Hello, I'm Hamza
A results-driven Data Scientist with a passion for building intelligent systems and extracting valuable insights from complex data. I specialize in Machine Learning and AI, with a focus on real-world applications.
Explore My WorkA results-driven Data Scientist with a passion for building intelligent systems and extracting valuable insights from complex data. I specialize in Machine Learning and AI, with a focus on real-world applications.
Explore My WorkPython, C, C++, Java, SQL, NoSQL
Pandas, NumPy, Scikit-learn, TensorFlow, Keras, Computer Vision
CNNs, Text Preprocessing, Information Retrieval, LangChain, LangGraph, RAG Pipelines, NLP
Jupyter, Colab, FastAPI, Vercel, Git, GitHub, Docker, Supabase
Matplotlib, Seaborn, Plotly
C++, Microcontrollers, Arduino, Selenium
BeautifulSoup, Selenium, Requests
I graduated with top honors from MC Boys School Kiri Dawood Khan, Multan in 2020, where I was recognized as the school topper.
I completed my FSC in Pre-Engineering in 2023 from Millat Associate College Multan, further strengthening my analytical and problem-solving skills.
I am currently in my second semester at Emerson University Multan, studying BS DS (Data Science), and achieved a perfect 4.0/4.0 GPA in my first semester.
Issued by Simplilearn
Issued by Simplilearn & Google Cloud
Issued by Simplilearn
Issued by Cisco Networking Academy
Compares two documents and tells you how similar they are using NLP, NLTK, spaCy, CountVectorizer, and Cosine Similarity.
A movie recommendation system powered by NLP and cosine similarity, built on a FastAPI backend and hosted on Hugging Face Spaces.
An AI-powered music recommendation app that uses NLP and TF-IDF to suggest songs based on text input. Built with Streamlit and FastAPI.
A book recommendation engine utilizing NLP to suggest books based on user queries, with a backend built on FastAPI and deployed on Hugging Face Spaces.
Developed a machine learning model that predicts diabetes with 97% accuracy, showcasing expertise in classification algorithms and model optimization.
Engineered a machine learning model to predict passenger survival on the Titanic, utilizing feature engineering and ensemble methods to achieve high predictive accuracy.
Built a Convolutional Neural Network (CNN) to classify the quality of bananas from images, demonstrating proficiency in computer vision and deep learning with Keras.
Created an NLP pipeline for emotion and sentiment analysis from text, applying techniques like tokenization, vectorization, and model training to extract insights from unstructured data.
Developed a robust email classifier using natural language processing (NLP) to accurately distinguish between spam and legitimate emails, a practical application of text-based classification.
Designed and built a full-stack application that leverages Retrieval-Augmented Generation (RAG) and an LLM to answer complex questions from any uploaded PDF, highlighting a strong grasp of modern Generative AI techniques.