Process discovery, i.e., learning process models from event logs, has attracted the attention of researchers and practitioners. Today, there exists a wide variety of process mining techniques that are able to discover the control-flow of a process based on event data. These techniques are able to identify decision points, but do not analyze data flow to find rules explaining why individual cases take a particular path. Fortunately, recent advances in conformance checking can be used to align an event log with data and a process model with decision points. These alignments can be used to generate a well-defined classification problem per decision point. This way data flow and guards can be discovered and added to the process model.