A paper titled Predicting risky driving behavior with classification algorithms: results from a large-scale field-trial and simulator experiment authored by Thodoris Garefalakis, Eva Michelaraki, Stella Roussou  Christos Katrakazas, Tom Brijs and George Yannis has been published in European Transport Research Review. The study analyzed large-scale data from real-world driving and simulator experiments, highlighting that models can predict dangerous behaviors, such as speeding and harsh braking, with accuracy rates as high as 84%. The findings emphasize the importance of using data-driven approaches to anticipate and mitigate risky behaviors, which are a leading cause of road crashes. This research reinforces the need for innovative tools to create safer driving environments and reduce accident risks.