Data Scientist | Python | Machine Learning | NLP | Scikit-learn | Streamlit | Open to Opportunities
- Data Scientist with hands-on experience in Python, Machine Learning, and NLP. Built end-to-end projects including mental health score, spam detection, sentiment analysis, and laptop price prediction systems. Experienced in building and deploying ML applications.
Career Goal: Seeking internship and full-time opportunities to build strong expertise in data science, machine learning, and AI while contributing to impactful projects, with the goal of growing into a successful Data Scientist.
| Programming | Data Analysis | Machine Learning | Tools |
|---|---|---|---|
| Python | Pandas, NumPy, Matplotlib, Seaborn and EDA | Scikit-learn, Regression & Classification | Git, GitHub, Jupyter and VS Code |
Upcoming Skills:
- Advanced SQL & Database Management
- Deep Learning & Neural Networks
- Generative AI Applications & LLMs
- Agentic AI Systems & AI Automation
- An End-to-End Machine Learning Project for Predicting Student Mental Health Score using Social Media Usage, Lifestyle Habits, and Academic Information.
- The project demonstrates a complete end-to-end machine learning workflow including data preprocessing, exploratory data analysis, feature engineering, model training, regression model comparison, evaluation, REST API development using FastAPI, and an interactive frontend developed with HTML, CSS, and JavaScript.
- 🔗 mental-health-score
- Built a laptop price prediction pipeline to estimate market prices based on key hardware features, comparing multiple regression models where XGBoost achieved the best performance with an R² score of 0.87.
- Applied feature engineering and EDA using Pandas, NumPy, Matplotlib, and Seaborn.
- 🔗 laptop-price-predictor
- Developed an NLP-based Email/SMS Spam Detection system to identify and filter unwanted messages, achieving 97% accuracy and 94% precision using Multinomial Naive Bayes.
- Compared 5 ML models and evaluated performance using key classification metrics.
- Deployed a real-time spam classification web app with Streamlit Cloud.
- 🔗 email/sms-spam-classification
- Predicted positive and negative sentiment from customer reviews and feedback using TF-IDF vectorization on 50,000 IMDb reviews.
- Logistic Regression achieved 88% test accuracy, outperforming other models through evaluation using accuracy and confusion matrix metrics.
- Deployed an interactive Streamlit app for real-time sentiment prediction.
- 🔗 movie-review-sentiment-analysis
- Bachelors in Computer Science – Shah Abdul Latif University (2020–2023)
📫 Contact:
- 📞 +92-308-3484370
