Northwestern Master of Science in Machine Learning and Data Science (formerly MSiA) | Practicum 2022 - 2023 | Center for Deep Learning

Production-ready ML system for vehicle price prediction achieving 96.82% R² accuracy with XGBoost, interactive Streamlit dashboard, and comprehensive drift monitoring

Automated Terraform cloud and enterprise drift detection

terraform / terragrunt drift detection

AI-powered Terraform lifecycle management with natural language to IaC conversion. Enterprise GitOps workflows with drift detection and auto-remediation.

A basic drift detection framework that uses KS test and PSI to look for data drift and also evaluates model performance.

Detect and summarize infrastructure drift across Terraform and OpenTofu projects.

Time‑aware NBA forecasting pipeline (R² 0.94 points) with rolling CV, leakage guards, and automated retraining; includes backtesting reports and model card.

Este proyecto ofrece un entorno completo para el análisis y monitoreo de drift en series temporales, complementado con herramientas de generación de datos sintéticos, técnicas de aumentación y evaluación de modelos predictivos.

In this project, we illustrate how the Kolmogorov Smirnov (KS) statistical test works, and why it is commonly used in Machine Learning (ML), Deep Learning (DL) and Artificial Intelligence (AI).

Agentic Drift, adaptive drift detection and AI reliability framework

Plant.ID: Molecular Identification of Plants

DynED is a novel ensemble construction and maintenance approach for data stream classification that dynamically balances the diversity and prediction accuracy of its components.

🌍Terraform Basics Tutorial 🌍 Master Terraform fundamentals to automate and manage your infrastructure efficiently! 🚀

🤖 Comprehensive AI Agent Evaluation Framework: Vanilla testing, monitoring & drift detection using OpenRouter. Features 5 test types, LLM-as-Judge, production monitoring, and 100+ model support.

PLD: Runtime Phase Model for Stable Multi-Turn LLM Systems

End-to-end MLOps: training → MLflow → containerized FastAPI → Helm+HPA → Prom/Grafana → drift checks → CI/CD with GitHub Actions

An application of the WhizML codebase for an analysis of Walmart weekly sales.

Production MLOps pipeline for Paris bike traffic prediction. Airflow orchestration, MLflow tracking (Cloud SQL), FastAPI deployment. Features: automated ingestion, drift detection, champion/challenger models, Prometheus+Grafana monitoring, Discord alerts. 15 Docker services locally.

Drift-Adaptive Behavioral Biometrics Framework for Continuous Authentication using Keystroke & Mouse Dynamics.