Many simulation and winner prediction methods were already proposed in the research area of basketball. A goal of a realistic simulation is the compliance of generated statistics dynamics with the statistic dynamics from real games. Our approach describes team statistics in different time-result situations. We research the transfer of statistics analysis corresponding to a situation and their usefulness in simulation. In the first part we develop models that approximate the behaviour of teams. In the second part we connect the obtained approximations with the model that predicts the next event in a basketball game. This model helps us create simulations, which we compare with the actual course of basketball games. The situational playing style modelling approach has generally not proven to be successful in generating realistic simulations.
|
