Process Mining Café

How exactly are people performing their analyses? Are they first exploring or immediately answering questions? And how do they deal with new questions that come up in the process? Pnina Soffer, Barbara Weber and Francesca Zerbato share their experiences from this new sub-field in the process mining research area.

Garbage in, garbage out! Data quality is essential for any data analysis technique. If you base your analysis on data, you must ensure that the data is correct. Otherwise, your results will be wrong. With Kanika Goel and Niels Martin, we talk about the specific data quality problems you encounter in process mining projects.

Project-driven organizations like construction companies approach everything from a project perspective. However, process improvement initiatives require process awareness. How do you deal with this as a process mining practitioner? We speak with Fred van Middendorp about project vs. process thinking.

What if you had twice as many people? What if you didn't do that process step? Simulation allows you to test complex “what if”-scenarios without having to make the change in the real world (yet). But it's not easy! Together with Lambros Viennas and Sudhendu Rai we show how you can use process mining as a starting point for your simulation model.

Process mining may not be the right tool for fraud detection. However, it can help us understand what happened after an attack, for example, by visualizing the intruder's path. Lucas Vousten and Vincenzo Salden talk about how process mining can help IT security and dive into a concrete forensics example based on a ransomware attack.

The Lean Six Sigma methodology provides a practical and customer value-focused framework for making improvements. Rudi and Anne talk about how process mining fits into Lean and Six Sigma, based on a concrete example. We also discuss where process mining changes the traditional Lean Six Sigma approach.

Organizational change is hard. As a process miner, you run into this challenge as soon as you have identified potential improvements and need to implement them. How do you get people on board? And how do you get them to stick with you in the new way? We talked with Sebastiaan van Rijsbergen and Roger Schmid about the strategies that have worked for them.

Stefanie Rinderle-Ma showed us how their open source process engine steers production processes. A nice side-effect of their system is that it collects data that can be used for process mining again! We also talked about the power of domain knowledge, how process mining can leverage sensor data, and realistic expectations for automation.

When you analyze a data set with process mining, you take a process perspective on your data. This perspective is determined by what you choose as the case ID, activity name, and timestamp during the import step. Marco Montali talks with us about the various process mining perspectives and their ontology-based data extraction approach.

Process miners need to be aware of their responsibility, both around the data and in how they present their analysis results. Together with Dirk Fahland and Felix Mannhardt we share many practical tips that you can start implementing today. We also discuss new research in the area of responsible data science.

There is often a divide between the strategy and the execution world in process mining. The people who are dealing with strategy are different from the people who are executing. Bogdan Ciungu joined us to discuss how organizations can bridge this divide. We talk about use cases, RFIs, and we show a concrete example for a business case.

Introducing process mining at an organization is never easy. Together with Vincent, Lewis, and Richard we talk about the strategies that worked for UWV, and about the success factors for one concrete project. All their tips are relevant not only for public administrations but for all organizations who want to introduce process mining.

What can you do if your data — at least at first sight — does not seem suitable for process mining at all? You look for “sequences of stuff”. Léonard Studer shares three examples of how he transformed problematic data, created non-existent data from file system logs, and even manually transcribed data in different scenarios.

Healthcare is a very interesting but also challenging application area for process mining. For example, a data set with 1000 cases can easily have 1000 variants, because every patient follows a unique path. Together with Luise Pufahl and Fran Batchelor we discuss the specific challenges of the healthcare domain along the phases of a typical process mining project.

Legacy systems are old, often mission-critical systems that can cause quite some headaches for their owners. Replacing these old systems is not easy, precisely because so much knowledge has been poured into them. Derek Russell and Steve Kilner joined us to talk about the different approaches to legacy system mining.

In a customer journey analysis, you look at the process from the viewpoint of the customer. Daisy gives us an overview about her recent analysis of the user journey on the “Start a Business” part of the GOV.UK website, and Rudi takes us through the three main challenges that you will encounter when you analyze customer journeys with process mining.

Our conversation with Hajo Reijers, Professor for Business Process Management & Analytics at Utrecht University. We talked about how processes are made of people, his interest in empirical research methods, industry cooperations with master students, two new research papers from this year and many other things.

Imagine your company introduces a new IT system and you have the opportunity to influence the data that will be collected. You want to make sure that the data is suitable for your process mining analyses in the future. Which data properties exactly will you need to ensure in the new system? We made a checklist for you, so you don't forget something essential.