A Cross-Organizational Process Mining Framework

Groups of people collaborate within organizations to deliver value to their customers. To establish such collaborations, which can lead to valuable outcomes for customers, a set of coordinated activities, events, and decision points are orchestrated in business processes. However, due to the diverse contexts of organizations, the meaning of terms used in business processes often differ from one organization to another. Moreover, the way a business process is executed may differ across organizations, in some branches of the same organization, or for certain products or services offered to customers, or even across organizational units. Those differences, furthermore, affect both the performance of business processes and the relevance of performance indicators used for measuring that performance. Therefore, when such points are not taken into account, efforts to enable organizations to learn from each other for performance improvement can lead to three main issues, namely unfairness, inaccuracy, and inadequacy. The aforementioned issues inspire the work in this thesis. In particular, the thesis focuses on providing relevant insights for organizations to improve their performance by learning from each other. With the theoretical Cross-Organizational Process Mining Framework that we developed, that learning becomes possible for organizations. The main contributions of this thesis are five approaches. The approach for automatically deriving Key Performance Indicators (KPIs) from Ontological Enterprise Models deals with the unfairness issue. Inaccuracy is the main focus of the approach for predicting relevant KPIs for organizations. Identifying the perspectives that can be adequate for organizations to learn from each other is the main focus of the two other approaches: the approach for the automated generation of engaging dashboards and the approach for interactive process performance dashboard generation. The last approach is devoted to building process benchmarks for performance improvement such that organizations can benefit from each others' best practices. Each approach is applied in a real-life setting to show its usefulness and practical value. Overall, the work presented in this thesis provides important contributions to perform cross-organizational process mining in a fair, accurate, and adequate fashion