This paper deals with prediction models of pedestrian crossing decisions aimed to be used later within autonomous vehicle safe speed control strategies. The emphasis is on stochastic models capable of capturing the inherent uncertainty and variability typically present in real pedestrian behavior. Instead of predicting whole pedestrian crossing trajectory, for the purpose of simplicity only ego-vehicle relevant quantities are targeted for prediction, i.e., a pedestrian entry time to and exit time from the crossing area, as they determine the pedestrian time occupancy of the conflicting crossing area where potential collision could happen. To this end, two independent feedforward neural network models are employed, targeted for prediction of conditional probability distributions of the aforementioned quantities in dependence on different vehicle- and pedestrian-related inputs. Finally, the proposed models are parameterized and verified for a single-vehicle/single-pedestrian case, based on data generated from numerous simulations of available game theory-based pedestrian model, where the vehicle is driven in an open-loop manner.