Process mining sits at the fascinating intersection of data science and business process management. It’s a field that uses event log data — records of activities executed within information systems — to discover, monitor, and improve real-world processes.
What Makes Process Mining Different?
Unlike traditional process modeling, which relies on interviews and manual documentation, process mining works with actual data. It tells you what really happens in a system, not what people think happens. This distinction is crucial: organizations often discover significant gaps between their documented processes and the reality captured in their logs.
The field generally breaks down into three main types of analysis:
- Process discovery — automatically constructing a process model from event logs
- Conformance checking — comparing an existing model against event logs to identify deviations
- Enhancement — extending or improving existing models using additional information from the logs
Why I’m Researching This
My interest in process mining stems from its potential to bridge the gap between computational methods and organizational improvement. As part of my work on “A Survey on the State of the Art in Process Mining” with J. C. Tejada Orjuela, I’m mapping the current landscape of techniques, tools, and applications in the field.
What excites me most is how process mining connects to broader questions about efficiency, transparency, and decision-making in organizations — questions that resonate with my background in both physics (mathematical modeling) and political science (institutional analysis).
Looking Ahead
In future posts, I’ll dive deeper into specific process mining techniques and share insights from my ongoing research. If you’re interested in the topic or working on related problems, I’d love to connect.