ONNX

Calibration, SHAP, and ONNX: Building a Delay Predictor That's Actually Honest

ROC-AUC tells you how well a model ranks flights by delay risk. It doesn't tell you whether a 40% prediction means 40% of flights actually get delayed. Those are different properties, and the second one matters when you're building a risk gauge. This tutorial covers isotonic probability calibration, SHAP explanations per prediction, ONNX export with a parity test, and why all three belong in the same ML lifecycle.

Advanced
40 minutes
Aug 10, 2026

Flight Disruption Intelligence: A Full-Stack Delay Predictor on Public Data and Free Infrastructure

An end-to-end flight delay prediction platform spanning medallion lakehouse, calibrated LightGBM with SHAP explanations, Spark Structured Streaming, dbt reliability marts, FastAPI serving, and a SvelteKit dashboard — built entirely on public BTS/NOAA/OpenSky data, self-hostable for $0/year, with a contract module that enforces leakage prevention across every pipeline stage.

VitalCheck API: Building a Multi-Domain Health Intelligence Engine with Python, FastAPI, and Production-Grade ML

VitalCheck is a production-deployed REST API that delivers real-time health risk assessments across ten medical and wellness domains. Built with Python, FastAPI, and a suite of machine learning models, it provides a unified interface for clinical and biometric predictions — from diabetes and stroke risk to MRI-based brain tumor classification.

    Ask me anything!