A Comparison of Deep-Learning Methods for Analysing and Predicting Business Processes
This work addresses the need for reliable process prediction in business analytics, but it is incremental as it compares existing methods on a new evaluation framework.
The paper tackled the problem of predicting next activities and timestamps in business processes using deep-learning methods, finding that a simple Multi-layer Perceptron often outperformed more complex models like Graph Neural Networks across different process stages.
Deep-learning models such as Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) have been successfully used for process-mining tasks. They have achieved better performance for different predictive tasks than traditional approaches. We extend the existing body of research by testing four different variants of Graph Neural Networks (GNN) and a fully connected Multi-layer Perceptron (MLP) with dropout for the tasks of predicting the nature and timestamp of the next process activity. In contrast to existing studies, we evaluate our models' performance at different stages of a process, determined by quartiles of the number of events and normalized quarters of the case duration. This provides new insights into the performance of a prediction model, as they behave differently at different stages of a business-process. Interestingly, our experiments show that the simple MLP often outperforms more sophisticated deep-learning models in both prediction tasks. We argue that care needs to be taken when applying automated process-prediction techniques at different stages of a process. We further argue that researchers should reflect their results with strong baselines methods like simple MLPs.