Bram Vanschoenwinkel AE, Belgium

Bram is one of the process mining veterans. He presented three case studies in payroll accounting, public administration, and postal services, and shared tips, tricks, problems he encountered, and lessons learned.

This talk is brought to you by:

Disco is the new complete process mining software from Fluxicon. Easy to use, lightning fast, and simply fun.

See for yourself why Bram Vanschoenwinkel and many others are using Disco, and download a free demo version today.

Fireside chat with Bram Vanschoenwinkel

As a warm-up for Process Mining Camp 2012, we asked some of the speakers for an up-front interview.

Anne: Can you still remember where and when you first heard about process mining? What exactly caught your attention and fascinated you about the topic?

Bram: I don’t remember exactly when I first heard about process mining, but it must have been somewhere late 2008 or early 2009. At that time I was working for a Belgian management consultancy firm with a strong methodological focus on facts, figures and measurable benefits. In that context, we were always looking for new techniques with a quantitative approach to process analysis. Indeed this is one of the strong points of process mining and thus the right combination of keywords inevitably led Google to direct me to a number of papers by Prof. dr. Wil van der Aalst (and others from the same group at the TU/e), ProM, and the website.

Since I have a backgorund in Machine Learning and Data Mining, I was immediatly fascinted about the topic and it also met our requirements in the search for innovative, quantitative process analysis techniques. Particulary the promise to discover AS IS process models very fast and based on facts rather than opinions caught my attention. It looked to me like such discovered process models could serve as the ideal starting point for change, i.e. a basis for further analysis and reflection with the business.

Anne: It’s interesting that you come from a machine learning and data mining background. Sometimes, people are confused about the relationship between process mining and data mining. Do you see process mining as a special data mining technique, or how else would you explain the difference to someone who is new?

Bram: Indeed, for me process mining is a particular form of data mining. Just like text mining and web mining are particular forms of data mining, where the same (or at least similar) techniques are used but specifically tailored to text/web data and corresponding applications.

For me, the main difference is in the representation and preprocessing of the data as well as in the representation and visualisation of the output. Of course, not all techniques that are used will be the same or similar and, therefore, another way to look at this is by considering a simple but generally accepted definition of data mining: “Data Mining is the nontrivial extraction of implicit, previously unknown, and potentially useful information from data.” And isn’t that exactly what process mining is doing?

Anne: Right! Since you said that you have worked with multiple analysis techniques techniques in the past, I would be curious which other techniques you are currently using next to process mining?

Bram: In a more clasical approach to process analysis I typically start by a number of interviews (collect information) and workshops (validate/complete/correct collected information) to get insight into the processes at stake, i.e. both the process flow as well as all relevant information related to the process.

Next, depending on the objectives of the analysis, I use different techniques to analyse the process. For example, Six Sigma to reduce the number of errors or throughput time and improve the stability/predictability of the process, Lean to detect and eliminate waste in the process, workload measurement to optimize resource allocation, time-driven activity based costing, simulation etc. In fact I also do these kind of things when I am using process mining. The big difference is that with process mining I can start from a solid basis for my interviews and workshops and I can easily set up different ‘experiments’ to further analyse the process with one of the analysis techniques I mentioned before.

Before I knew process mining, I also used information from the applications that support the process. But with process mining it becomes easier to fully exploit this information and focus on what is really important: Actually improving the process. So for me process mining is not a standalone technique, but complementary to other techniques and a starting point for change.

Anne: Thanks a lot, Bram!

Process Mining Camp 2012.

We had a great time at Process Mining Camp 2012, which was held on 4 June in Eindhoven, The Netherlands. Catch a flavor of the talks at Process Mining Camp 2012 below!

Process Mining Camp 2012 was organized by Fluxicon and supported by TU Eindhoven, the IEEE Task Force on Process Mining, the Ngi, and the BPM Roundtable. We also want to thank Elham Ramezani and Tijn van der Heijden for their great support.

Why camp?

Process Mining Camp is where professionals gather to learn from seasoned experts. A place where you can meet fellow explorers and exchange ideas and business cards. Old-timers and greenhorns alike, this is where we get down to business and share stories from the frontier at the campfire.

Whether you are an expert or have just recently heard of process mining, here you can meet other people who are just as curious and passionate about process mining as you are. Learn about how others are using process mining, and what they have to tell you.

Christian W. Günther Fluxicon, Netherlands

The Fluxicon co-founder welcomes the campers with a story about process mining in the 19th century and shares some glimpses of our vision for process mining.

Video and details

Frank van Geffen Rabobank, Netherlands

Frank is applying and promoting process mining within the Rabobank. He told us about the added value he has found, and also about organizational challenges, like identifying the right people.

Video and details

Mieke Jans Deloitte Analytics, Belgium

Mieke has not only a PhD in process mining, but also lots of experience with projects with an auditing focus. At camp, she shared the seven steps she is using in her process mining projects in an audit context.

Video and details

Léonard Studer City of Lausanne, Switzerland

Léonard is setting up an internal control system using process mining at the City of Lausanne. He talked about the benefits of process mining in a resource-constrained environment.

Video and details

Wim Leeuwenkamp Dutch Tax Office, Netherlands

Wim shared his experiences from a pilot project in the audit department of the Ministry of Finance in the Netherlands. He told us about the challenges involved in the construction of event logs in a legacy environment.

Video and details

Bram Vanschoenwinkel AE, Belgium

Bram is one of the process mining veterans. He presented three case studies in payroll accounting, public administration, and postal services, and shared tips, tricks, problems he encountered, and lessons learned.

Video and details

Anne Rozinat Fluxicon, Netherlands

Anne showed us how a typical process mining analysis looks like, live on stage. She quickly simplified a complex service refund process data set, cleaned incomplete cases, and tracked down a bottleneck in the forwarding company.

Video and details

Wil van der Aalst TU Eindhoven, Netherlands

Wil is an icon in the field of process mining, and he is heading the leading process mining research group at TU Eindhoven. He gave us an exclusive overview about current research from his process mining group.

Video and details