AI for airports
two systems ·
Usage forecasting
Predicts daily passenger throughput. The service trains a seasonal baseline and a LightGBM model, backtests both, and serves whichever wins. Live numbers come from the forecasting API, with a sample fallback when it is offline.
Security assistant
A retrieval-augmented chatbot for airport-security questions. It answers from a document index and cites sources — and refuses when the answer is not grounded, instead of guessing (try the last two below). Sample answers shown when the API is offline.
About
usage-forecasting
FastAPI service forecasting passenger throughput. Seasonal baseline today, LightGBM on calendar + lag features next. Public TSA data first; real airport data later.
security-assistant
RAG over a document index + structured DB. Cites sources, refuses when not grounded. Provider-agnostic LLM: local Ollama for dev, Claude for production.