Masking Neural Networks Using Reachability Graphs to Predict Process Events
This work addresses event prediction in process mining, offering an incremental improvement over existing methods.
The paper tackles the problem of predicting the next event in process mining by proposing a method that integrates the process model structure more deeply into the neural network of Decay Replay Mining, using a masking layer based on reachability graphs and architectural modifications, resulting in improved predictive performance as demonstrated experimentally.
Decay Replay Mining is a deep learning method that utilizes process model notations to predict the next event. However, this method does not intertwine the neural network with the structure of the process model to its full extent. This paper proposes an approach to further interlock the process model of Decay Replay Mining with its neural network for next event prediction. The approach uses a masking layer which is initialized based on the reachability graph of the process model. Additionally, modifications to the neural network architecture are proposed to increase the predictive performance. Experimental results demonstrate the value of the approach and underscore the importance of discovering precise and generalized process models.