The i-DREAMS project aims at defining, developing, testing and validating a “Safety Tolerance Zone” (STZ) in order to prevent drivers from getting too close to the boundaries of unsafe operation by mitigating risk in both real-time and post-trip. Τhe aim of the current study is to provide guidelines for mapping the concept of the STZ using continuous variables of risk and the most reliable indicators (e.g. time headway, speed, harsh acceleration, distraction) are going to be investigated in real-time. For the purpose of the analysis, a variety of analytical methods and potential modelling approaches are proposed. According to the research question made, a mapping exercise of machine learning algorithms (e.g. Long Short-Term Memory or Dynamic Bayesian Networks) is implemented for real-time data prediction. The key output will be the correlation of the aforementioned explanatory variables and various indicators of task complexity and coping capacity with the dependent variable risk.