22 citations · 29 across the 11 of their papers we have counts for
7 papers · 1 filter
Leveraging Duration Pseudo-Embeddings in Multilevel LSTM and GCN Hypermodels for Outcome-Oriented PPM
Fang Wang, Paolo Ceravolo, Ernesto Damiani
Existing deep learning models for Predictive Process Monitoring (PPM) struggle with temporal irregularities, particularly stochastic event durations and overlapping timestamps, lim…
HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
Fang Wang, Paolo Ceravolo, Ernesto Damiani
We propose HGCN(O), a self-tuning toolkit using Graph Convolutional Network (GCN) models for event sequence prediction. Featuring four GCN architectures (O-GCN, T-GCN, TP-GCN, TE-G…
Comprehensive Attribute Encoding and Dynamic LSTM HyperModels for Outcome Oriented Predictive Business Process Monitoring
Fang Wang, Paolo Ceravolo, Ernesto Damiani
Predictive Business Process Monitoring (PBPM) aims to forecast future outcomes of ongoing business processes. However, existing methods often lack flexibility to handle real-world…
Tailoring Machine Learning for Process Mining
Paolo Ceravolo, Sylvio Barbon Junior, Ernesto Damiani +1
Machine learning models are routinely integrated into process mining pipelines to carry out tasks like data transformation, noise reduction, anomaly detection, classification, and…
Trace Encoding in Process Mining: a survey and benchmarking
Sylvio Barbon, Paolo Ceravolo, Rafael S. Oyamada +1
Encoding methods are employed across several process mining tasks, including predictive process monitoring, anomalous case detection, trace clustering, etc. These methods are usual…
Selecting Optimal Trace Clustering Pipelines with AutoML
Sylvio Barbon, Paolo Ceravolo, Ernesto Damiani +1
Trace clustering has been extensively used to preprocess event logs. By grouping similar behavior, these techniques guide the identification of sub-logs, producing more understanda…
Using Meta-learning to Recommend Process Discovery Methods
Sylvio Barbon, Paolo Ceravolo, Ernesto Damiani +1
Process discovery methods have obtained remarkable achievements in Process Mining, delivering comprehensible process models to enhance management capabilities. However, selecting t…