The selective control of the frictional behavior (tailored friction) in metal forming processes is of high importance with regard to technical and economic aspects. This applies especially for the sheet-bulk-metal forming process. Milling with intentionally invoked regenerative tool vibrations can be applied in order to generate structured surfaces with tailored friction properties on the forming tool. These structures affect the formation of lubrication pockets during the forming process which determine the local frictional properties exceedingly. The full potential of this emerging technology can, however, only be revealed if the heuristic and design-relevant knowledge is acquired and provided to the tool-designer already in the early phases of process development. One thing the tool-designer has to specify is the local frictional behavior on the tool surface. But, however, he does not know which milling parameters lead to the necessary surface structures because in most cases he has no expert knowledge in milling, tribology and forming tools. In this paper data mining is used to determine the frictional behavior based on these parameters. The potential of this method in the described context is revealed by the application on data derived from simulation results, both from milling simulations and contact simulations. The latter are performed by using a Halfspace model for rough surface contact. Both approaches for these simulations, the data mining process and the results are explained to the reader.