Engineered a containerized ML platform (FastAPI + Node.js, Docker Compose) with multivariate anomaly detection (LOF, One-Class SVM, PyTorch autoencoder), category-level forecasting (XGBoost/RF/GBM), Jensen Shannon drift detection, and sentence-transformer semantic clustering via REST APIs processing 10,000+ transactions in ∼3s.
nodejs javascript python docker docker-compose scikit-learn postgresql expense-tracker pandas restapi xgboost autoencoder financial-data gradient-boosting finance-management anomaly-detection fastapi expense-analysis
-
Updated
Aug 24, 2026 - Python