Process Mining Camp 2014 — Fireside Chat with Johan Lammers
As a warm-up for Process Mining Camp, we asked some of the speakers for an up-front interview. Camp tickets have been sold out now, but if you did not get one you can still sign up for the waiting list and we will notify you if seats become available. Let’s get ready for camp!
Previously, we already spoke with Frank van Geffen from the Rabobank.
Today, you can read the interview with Johan Lammers. Johan has been a business analyst and statistical researcher for almost 30 years and will give a practice talk at camp about his experience with process mining at the Centraal Bureau voor de Statistiek in the Netherlands.
Interview with Johan
Anne: Hi Johan, I have this booklet here – produced by the Centraal Bureau voor de Statistiek – with a nice collection of all kinds of statistics about the Dutch society. I never really thought about the fact that there are processes behind making such statistics. How important are processes at the CBS in general?
Johan: Hello Anne, in our business, processes have two faces: You can produce statistics about processes and processes are needed to produce statistics. The ‘Statistics’ tab in Disco gives an impression of the statistics you can produce. Our office is governmental and we use public finances. The efficiency and the effectiveness of our processes is important to spend that money well.
Anne: Right! So, the CBS is involved in process improvement initiatives? Can you give us an overview about the kinds of processes that you can find at CBS?
Johan: Our main ‘production line’ has three steps: Collection, analysis and publication. As we produce information (statistics), our main material is data. Data about lots of subjects in our society: Persons, enterprises, goods, services, cars, roads, etc. In order to produce, we have to design. This involves the design of the production process and of the methodology. A huge part of our processes is automated, manual intervention only applies when relevant for the quality of our products.
Anne: Yes, I can imagine. The main part simply must be automated to deal with the massive amounts of data that I imagine must be coming your way. Speaking of big data, I have seen more concerns recently about the validity of correlations that people find in data (or better, the causation they imply), illustrated, for example, by a statistically significant correlation between the divorce rate and the per capita consumption of margarine. As a statistics practitioner, are you worried about how people are using statistics today?
Johan: I’m ambiguous towards his question. On the one hand it’s a good sign that people are willing to use statistics. The trap is to rely solely on this source. The methodology to create reliable statistics is quite complex. Available tooling tends to make it more and more easy. It’s essential to apply a good share of common sense though. The development of data science is very important to create valuable knowledge with an appropriate role for statistics. In my opinion, process mining contributes to this development.
Anne: Absolutely, I completely agree. And I am sure that we will see more awareness for methodology and more maturity in the field over time. Thanks a lot for making the time for this chat. We are all very curious to hear more about your process mining experiences at camp!
Would you like to hear more from Johan about his experiences? Are you interested in sharing first-hand knowledge with fellow process miners? Sign up now for the waiting list for Process Mining Camp on 18 June in Eindhoven. A few more tickets might become available…