Machine LearningKarachi AQI Forecasting System
Production-oriented serverless ML system forecasting Karachi AQI at 24h, 48h, and 72h horizons using Open-Meteo, BigQuery, GCS, GitHub Actions, and Streamlit.
/THE PROJECTS
Exploring what’s possible with AI, machine learning and data. A closer look at the problems, the process and the work.
7 projects
Machine LearningProduction-oriented serverless ML system forecasting Karachi AQI at 24h, 48h, and 72h horizons using Open-Meteo, BigQuery, GCS, GitHub Actions, and Streamlit.
AI EngineeringFull-stack university admissions platform with AI-powered recommendations, RAG chatbot support, document ingestion, and role-based application workflows.
Computer VisionCustom YOLOv8m computer vision system trained to detect and classify nine road-user categories from real-world Karachi traffic imagery for traffic analysis.
Machine LearningImplemented extractive (spaCy) and abstractive (Transformers) summarization; fine-tuned models and evaluated on news articles.
Machine LearningPreprocessing with imbalance handling (SMOTE), classifiers (LightGBM/SVM), and metrics reporting for lender recommendations.
Machine LearningBuilt classification models (Random Forest, Logistic Regression) with SHAP/LIME explainability to support HR retention decisions.
Machine LearningEDA, feature selection, scaling, and Gradient Boosting on PIMA/Heart Disease datasets with AUC-ROC evaluation.
Have a problem worth solving? Let’s talk about what we can build together.
Start a conversation