Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. However, most of this data is observational and collected without interventions, making causal questions like "How would rain change traffic density?" difficult to answer. We present teLLMe, a system for exploratory causal analysis of urban driving datasets.
The system starts from a structured event table built from dashcam annotations and combines causal structure learning with the PC algorithm, bootstrap-based stability checks, and query-specific effect estimation using linear regression and DoWhy. Natural-language questions are mapped to structured causal queries through a schema-aware LLM, enabling users to specify treatments, outcomes, and subpopulations.
teLLMe returns a "Causal Card" that summarizes effect estimates, adjustment sets, DAG support, and assumptions, followed by a short natural-language explanation. Case studies on BDD-derived traffic events show that the system can surface plausible relationships involving weather, peak hours, and traffic density, while making uncertainty and modeling choices explicit. The system is designed as a tool for hypothesis generation and expert reasoning rather than a source of definitive causal claims.
Blogger's Review: The innovation of the teLLMe system lies in its ability to simplify complex causal analysis into a user-friendly interface, allowing non-experts to engage in in-depth analysis of traffic data. This combination of machine learning and causal inference provides new perspectives and tools for urban traffic management. With effective modeling, traffic authorities can better understand the various factors influencing traffic flow, thereby optimizing traffic policies.