Numerical simulation plays a decisive role in the development of the continuous casting process, concerning the optimization of productivity and product quality. The precision of the simulation results is significantly influenced by the boundary conditions. At the Chair of Iron and Steel Metallurgy, simulation is carried out using the in-house developed software m2Cast. The so-called nozzle measuring stand is used to determine the heat transfer coefficient between the strand surface and the cooling water. Since it takes a considerable amount of time to carry out measurements for all time steps and the prevailing cooling conditions, equations are used for prediction. The aim of this work is to predict this coefficient more precisely by using regression models instead of conventional equations. For this purpose, different models were considered, and the existing data set was optimized. An additional input parameter should take into account the spray properties. These properties are recorded by implementing an impact weight measurement on the nozzle measuring stand. The impact weight is measured for a selected parameter field and then integrated into the existing data set. In addition, further investigations are realized using the impact weight measurement. ¿