Data Analyst / Junior ML Engineer building end-to-end projects from data cleaning to deployed models.
LinkedIn · affannadeem005@gmail.com
Currently completing my intermediate studies, building hands-on ML/data projects in my own time. I focus on shipping full pipelines data → model → deployment rather than stopping at a notebook. Open to internships, freelance work, and entry-level roles.
Predicts student math scores from 1,000+ records. Compared 7 algorithms (Random Forest, XGBoost, Gradient Boosting, etc.) with hyperparameter tuning via RandomizedSearchCV. Best model: 88% R². Served via Flask, deployed on AWS Elastic Beanstalk. Stack: Python, Pandas, Scikit-learn, XGBoost, Flask, AWS Repo →
Automated ML model deployment using Docker, AWS ECR/EC2, and GitHub Actions. Cut deployment time from 30+ minutes (manual) to 5 minutes (automated), with automated testing on every commit. Stack: Docker, AWS, GitHub Actions, Python, YAML Repo →
| Project | What it does | Stack |
|---|---|---|
| Titanic Survival App | Interactive Streamlit app, 80% classification accuracy | Python, Streamlit, Scikit-learn |
| Tesla Stock Prediction | Time-series analysis & forecasting on 5 years of price data | Python, Pandas, Scikit-learn |
| Retail Analytics — Black Friday | EDA + feature engineering, hypothesis testing on purchase behavior | Python, Pandas, Statistical Testing |
| Online Retail EDA | Customer segmentation (RFM), 500K+ transactions | Python, Pandas, Matplotlib |
Languages: Python, SQL
ML: Scikit-learn, XGBoost, Regression, Classification, Clustering, Hyperparameter Tuning
Deployment: Docker, AWS (EC2, Elastic Beanstalk, ECR), Flask, Streamlit, GitHub Actions/CI-CD
Data & Viz: Pandas, NumPy, Matplotlib, Seaborn, Power BI, Tableau
LLM applications, RAG, and AI agent workflows (LangChain) — planning to ship a project here in the coming months.
- Freelance Projects on Upwork (ML, Data Science, Deployment)
- Contract Work (part-time, full-time)
- Internships (Data Science, ML Engineering)
- Collaboration (open source, side projects)
"Transforming raw data into production ML systems."
⭐ If you found this useful, please star my repos!