Making sense of data: leveraging AI to empower data-driven decision making in public transport

Public transport authorities collect vast amounts of data on travel behavior. However, effectively utilizing this data is challenging. This paper addresses this challenge by presenting an AI-based data management tool prototype designed to support public transport authorities in making better use of their data. The tool leverages large language models (LLMs) and retrieval-augmented generation (RAG) to provide functionalities such as uploading data, querying, summarizing, and chatbot interaction. The paper discusses the development process, user needs and challenges identified, and the findings from user evaluations. The evaluation results indicate that the tool has the potential to improve data accessibility, user understanding of travel patterns, and collaboration among stakeholders, while acknowledging the need for user awareness of the tool’s limitations.