Event log-based activity and resource recommendation for running business processes: a meaningful explanation-driven framework

• Grant number: 20/11224-0
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: January 01, 2021
• End date: June 30, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Marcelo Fantinato
• Grantee: Ana Rocío Cárdenas Maita
• Host Institution: Escola de Artes, Ciências e Humanidades (EACH). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

The combination of Business Process Management (BPM) and data mining has established a research field known as process mining. The goal of process mining is to extract knowledge about data obtained from the work carried out at different stages of the BPM life-cycle. Process mining seeks to improve business processes by discovering links between variables and behavioral patterns. The data to be mined are usually formed of event logs produced by the information systems used by organizations. Although there has already been a significant improvement regarding techniques developed specifically for process mining, a current challenge is to explain details of the decision making performed by the algorithm when producing the recommendations. The current results show greater accuracy in predicting the next activity and resource to run instances. Even studies in this field were carried out in our research group. Despite this, achieving interpretable and explainable results in process mining context remains a major challenge. Therefore, this research project aims to develop a meaningful explanation-driven framework for event log-based activity and resource recommendation for running business processes. (AU)