An entropy-based model selection framework and DAW-Transformer achieve better next activity prediction on high-entropy event logs, with interpretable models sufficing for low-entropy ones.
Next activity prediction and elapsed time prediction on process dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Innovative Next Activity Prediction Using Process Entropy and Dynamic Attribute-Wise-Transformer in Predictive Business Process Monitoring
An entropy-based model selection framework and DAW-Transformer achieve better next activity prediction on high-entropy event logs, with interpretable models sufficing for low-entropy ones.