Each case study explains the business problem, project scope, workflow, analysis focus, conclusions, repository assets, and a direct path to discuss similar work.
Built a retrieval-augmented assistant that grounds LLM responses in trusted medical reference materials using document processing, embeddings, semantic search, vector storage, and controlled prompting.
Developed an end-to-end retail sales forecasting workflow spanning feature preparation, regression modeling, tuning, API packaging, containerization, and interactive delivery.
Created a safety-helmet image classifier using CNNs, transfer learning, fine-tuning, and data augmentation to support automated workplace compliance monitoring.
Designed neural-network classifiers for wind-turbine generator failure prediction with class-imbalance handling and recall-focused evaluation for proactive maintenance.
Built an ensemble-learning solution to predict visa application outcomes using bagging, boosting, stacking, hyperparameter tuning, and feature-importance analysis.
Developed a customer-propensity model for personal-loan targeting using exploratory analysis, feature preparation, classification models, and business-oriented evaluation.
Performed end-to-end exploratory analysis of food-delivery orders to uncover customer behavior, restaurant performance, cuisine demand, ratings, delivery patterns, and revenue opportunities.