An Innovative Next Activity Prediction Using Process Entropy and Dynamic Attribute-Wise-Transformer in Predictive Business Process Monitoring
📰 ArXiv cs.AI
Next activity prediction in business process monitoring uses process entropy and dynamic attribute-wise-transformer for improved accuracy and interpretability
Action Steps
- Calculate process entropy to quantify the complexity of event logs
- Apply dynamic attribute-wise-transformer to capture evolving patterns in event data
- Use the entropy-based model selection framework to choose the most suitable model for next activity prediction
- Evaluate the performance of the selected model using metrics such as accuracy and interpretability
Who Needs to Know This
Data scientists and business analysts on a team can benefit from this approach to improve operational efficiency and decision-making, as it provides a framework for selecting the most suitable model for next activity prediction
Key Insight
💡 Process entropy can be used to select the most suitable model for next activity prediction, balancing accuracy and interpretability
Share This
📈 Improve next activity prediction in business process monitoring with process entropy & dynamic attribute-wise-transformer!
Key Takeaways
Next activity prediction in business process monitoring uses process entropy and dynamic attribute-wise-transformer for improved accuracy and interpretability
Full Article
Title: An Innovative Next Activity Prediction Using Process Entropy and Dynamic Attribute-Wise-Transformer in Predictive Business Process Monitoring
Abstract:
arXiv:2502.10573v2 Announce Type: replace-cross Abstract: Next activity prediction in predictive business process monitoring is crucial for operational efficiency and informed decision-making. While machine learning and Artificial Intelligence have achieved promising results, challenges remain in balancing interpretability and accuracy, particularly due to the complexity and evolving nature of event logs. This paper presents two contributions: (i) an entropy-based model selection framework that
Abstract:
arXiv:2502.10573v2 Announce Type: replace-cross Abstract: Next activity prediction in predictive business process monitoring is crucial for operational efficiency and informed decision-making. While machine learning and Artificial Intelligence have achieved promising results, challenges remain in balancing interpretability and accuracy, particularly due to the complexity and evolving nature of event logs. This paper presents two contributions: (i) an entropy-based model selection framework that
DeepCamp AI