Projects

Multi-tenant AI learning platform for test prep academies. Socratic AI tutor that refuses to give answers, AI quiz generation from uploaded files, async pre-grading, weak-spot detection, and AI parent summaries. Full role-based platform across admin, instructor, student, and parent.

Production-grade fraud operations platform with calibrated LightGBM scoring at 8.5ms, SHAP explainability on every prediction, and $1.23M in modeled net savings from cost-aware threshold tuning.

Production-grade full-stack platform with role-based portals, real-time analytics, and a Random Forest model that predicts academic risk with 96% accuracy.

ML-powered crime pattern explorer for Chicago. 8.5M rows, 4 XGBoost models with SHAP explanations, beat-level heatmap, and an honest methodology page about what the data can and cannot tell you.

A controlled four-family architecture comparison (Swin T/S/B, RegNetY CNNs, EfficientNet B3-B7, ViT-B/16) on the Oxford-IIIT Pet Dataset under RTX 4090 constraints. Three findings: Swin's hierarchical attention transfers cleanly to small datasets (93.8-96.35%), EfficientNet's compound scaling breaks (B3 beats B7 by 8.66 points), and ViT catastrophically fails (7.17%: barely above the 2.7% random baseline).

MapReduce analytics on the UCI Online Retail II dataset using AWS EMR, Hadoop, Pig, and Hive.