Machine Learning & Data Science

Intelligent Question Answering for Traffic Information

A chatbot that answers natural-language questions about traffic news and conditions by querying real databases, using agentic RAG and text-to-query.

Chatbot screens answering traffic news and route questions on mobile

About the project

Research on natural-language question answering for traffic information. Users ask about traffic news or a route of interest; an agentic RAG pipeline built on a large language model turns the question into a database query (text-to-query), retrieves real data to answer it, and adds time-series forecasting.

Techniques

Agentic RAG · Large Language Model · Text-to-Query · Time Series Forecasting