Improving road safety prediction tools requires assessing established traffic simulation tools and safety assessment methods. Enhancing these tools with innovative data sources and methods can significantly reduce urban crashes and their impact. To achieve this, it is imperative to identify the requirements and gaps of relevant stakeholders in terms of professional road safety analysis tools. The present study aims to utilize association rule mining to determine underlying profiles of local stakeholders who are identified as hands-on practitioners. To accomplish this objective, a dedicated survey was conducted, and the data were analyzed to discover meaningful links among stakeholder characteristics through the characteristics mined using the Apriori algorithm. The results provide a quan-tification of the frequency and relationships between stakeholder responses, in-dicating connections between education levels, work regions, experience levels, and stakeholder needs related to road safety prediction tools. The study insights offer a quantitative perspective on the interconnections and dependencies among different stakeholder attributes, shedding light on potential patterns and prefer-ences that can guide decision-making in the context of road safety improvements.