European energy and ancillary service markets have recently undergone many changes. Some were structural, such as the go-live of balancing energy trading platforms MARI and PICASSO, while others, like price spikes, were consequences of world events. These changes may negatively impact tools that rely on data stationarity, especially machine learning-based models. We use the energy and ancillary service market data for Croatia, France and Germany to determine prerequisites for predicting manual frequency restoration reserve (mFRR) capacity and balancing energy prices. We present a statistical analysis of the data, and draw conclusions about the steps necessary for training machine learning models on this data.