Leveraging Shallow Machine Learning to Predict Business Process Behavior

Annalisa Appice, Nicola Di Mauro, Donato Malerba

Abstract: This study investigates facets of shallow machine learning as an accurate data-centric approach to predict business process behaviour. Shallow machine learning is investigated as a part of a holistic approach that combines feature construction, local and global learning, classification and regression algorithms. Experiments show that, despite the emerging attention towards deep learning also in predictive process mining, stacking feature construction and shallow machine learning algorithms can still outperform various process predictor competitors (included deep learning ones).