Outcome-Oriented Predictive Process Monitoring with Attention-Based Bidirectional LSTM Neural Networks

Outcome-oriented predictive process monitoring plays an important role for business process management, which is to predict the most likely outcome class (positive or negative) for an on-going case given the event log consisting of completed business process instances with labeled outcome classes. Unfortunately, the existing traditional machine learning methods for this problem require a lot of manual intervention and long time in real-time prediction applications. In order to construct a predictive classification model automatically, we propose an effective approach based on deep learning techniques, called Att-Bi-LSTM, which is combined with the bidirectional long short-term memory network and the attention-mechanism. This approach can capture and optimize the features that have a decisive effect on the outcome for a completed case so as to construct a predictive model with good performance. The extensive experiments conducted on twelve real datasets show that our approach outperforms the state-of-the-art ones in terms of prediction accuracy, earliness, and time performance.