ABSTRACT
This chapter presents a real-world case study based on Belgium’s railway traffic control centres. Building on an intense and continuous collaboration between researchers and practitioners, we produced the “Hourly Risk Index”: A risk-based model for the evaluation of staff rosters. The model was validated with large-scale traffic control data (containing close to 8 million round-the-clock working hours in the period 2013 to 2018). The validation exercise not only showed that the occurrence of safety-critical errors is significantly associated with higher Hourly Risk Index values, but also that error severity is significantly related to a further increase in risk. In addition, the Hourly Risk Index outperformed its predecessor, the Risk Index. Given these outcomes, the model is now being deployed and tested at Belgian national railways. It is also freely available in an open-source R package (FIPS). This should allow the further refinement of the Hourly Risk Index in an iterative manner.
