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

advanced Published 8 Apr 2026
Action Steps
  1. Calculate process entropy to quantify the complexity of event logs
  2. Apply dynamic attribute-wise-transformer to capture evolving patterns in event data
  3. Use the entropy-based model selection framework to choose the most suitable model for next activity prediction
  4. 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
Read full paper → ← Back to Reads

Related Videos

LANGGRAPH: Other Frameworks Are DEAD Now!
LANGGRAPH: Other Frameworks Are DEAD Now!
Thomas Janssen
Gemma 4 is the NEW Coding King: Setup Local AI Agents in VS Code (Full Guide)
Gemma 4 is the NEW Coding King: Setup Local AI Agents in VS Code (Full Guide)
Ksk Royal
How to Setup OpenClaw for FREE on Raspberry Pi 5 | Full Ollama & AI Agent Guide
How to Setup OpenClaw for FREE on Raspberry Pi 5 | Full Ollama & AI Agent Guide
Ksk Royal
How to Install Hermes Agent on Raspberry Pi 5 (FREE 24/7 AI)
How to Install Hermes Agent on Raspberry Pi 5 (FREE 24/7 AI)
Ksk Royal
Run Local Agentic AI on Mac with MLX (Private & Offline)
Run Local Agentic AI on Mac with MLX (Private & Offline)
Ksk Royal
NVIDIA GEAR SONIC Review: REVOLUTION in Humanoid Robots Movement System
NVIDIA GEAR SONIC Review: REVOLUTION in Humanoid Robots Movement System
MaxonShire