Sequences of Stuff

In last week’s Process Mining Café, we talked about finding events in unexpected places with Léonard Studer, an internal consultant for business process management at the City of Lausanne in Switzerland. You can now watch the recording here.

We talked about how looking for process mining data is essentially looking for “sequences of stuff”. Once you realize what the minimum requirements for process mining are, you start seeing possible process mining data everywhere.1

Léonard gave three examples of sequences of stuff that he has analyzed with process mining.

Sequences of circulations

In the first example, Léonard took data related to a building permit process from the ERP system at the city. Because the ERP data had no real activity name (just a free-text field), he started to analyze the data with a text mining tool. He ultimately broke down the process into circulations of files and used his understanding from the text mining to categorize the communications into ambiguous vs. non-ambiguous texts, which had a clear correlation to the duration of a case in the process.

Sequences of people

In the second example, there was no information system supporting the process at all. But Léonard still wanted to help the opera in Lausanne with their program management process. So, he looked at the creation and access of files via the Network Attached Storage (NAS) access log. From these access logs, the implicit communication flows between people – and the activity levels of the program creation process – could be analyzed.

Sequences of speeches

As a third example, Léonard looked at debates in the local parliament as a process: The activities were the speeches (or the parties); the cases were the topics that they debated.

Léonard also shared many practical tips about how to put people at ease when you start analyzing their work with process mining. For example, he first makes sure that they understand that the goal is to analyze the process – not the people. Then, he schedules a confidential session with the workers in the process without management. In this meeting, nothing leaves the room (like you would expect from a priest in a confession).

He has seen that, once the right steps are taken, process mining really helps the people to speak the truth about their process.

Thanks again to Léonard, and to all of you, for joining us!

Here are the links that we mentioned during the session:

  1. For example, Hadi once even analyzed sequences of ball passes in a football team! ↩︎

Process Mining Camp 2021

Process Mining Camp 2021

Here in Eindhoven, spring is finally coming to town. The days are slowly getting longer, and sometimes even more sunny. The birds are shouting it from the tree tops, the time has finally come, something to look forward to after a long, hard winter:

It’s time for Process Mining Camp!

From 31 May to 4 June, we will have ourselves a nice, relaxed week full of exquisite process mining fun. Once again, like we did last year, we will camp with all mod cons – from the comfort of our homes, over the trusty old internet.

We will be streaming live for a couple of hours each day, but the real action is around our Campfire on Slack. Get to know your fellow campers, and geek out about all things process mining, all around the clock.

Did you know that this year will be the 10th anniversary of process mining camp? A lot of things have changed since our first camp back in 2012, but the essence remains: In our practice talks, process mining professionals from all over the world will share their experiences with you. Straight from the heart, honest, and true – including everything but the sales fluff.

After each practice talk, and after Wil’s closing keynote, we will have a special edition of our world-famous Process Mining Café. Join the speakers of the day, along with some very special guests from the long and storied history of Process Mining Camp, as we dive deeper into some of the topics that make process mining so interesting.

As a special treat for the 10th anniversary edition of camp, Rudi has cooked up a surprise for us: The brand-new Process Mining Lab is for those of us who like to learn by doing, and those who prefer practice over theory. Stay tuned for this daily overdose of hands-on process mining from the hands of a mad scientist.

Exciting stuff, all around – and we can’t wait to tell you all the details in the days to come! Hurry up and sign up right now to join us at camp, so you don’t miss a thing!

Process Mining Café 6: Freestyle Data Transformation

Process Mining Café 6

Léonard Studer is an internal consultant for business process management at the City of Lausanne and a true process mining veteran. After having him as a speaker at our very first Process Mining Camp in 2012, we brought him back in 2015 with an honest and in-depth talk about their analysis of the construction permit process.

Along his journey in process mining, Léonard has developed a habit for finding data in rather unusual and unexpected places. We have asked him to join our next Process Mining Café to share his experiences of what else you can do if your data — at least at first sight — does not seem suitable for process mining at all. So, if you need some inspiration, or just want to hear his process mining war stories from the City of Lausanne, don’t miss our Process Mining Café next week!

Join us on Wednesday 28 April, at 16:00 CET! (Check your own timezone here).

As always, there is no registration required. Simply point your browser to when it is time. You can watch the café and share your thoughts and questions while we are on the air, right there on the café website.

Tune in live for Process Mining Café by visiting next week Wednesday 28 April, at 16:00 CET! Add the time to your calendar to make sure you don’t miss it. Or sign up for the café mailing list here if you want to be reminded one hour before the session starts.

Project Guide – Part 1: Process Selection

We have discussed a lot of practical process mining topics here on the blog over the past years, but one thing that is still missing is a step-by-step project guide. This is what this new series is all about.

  • Step 1: Process selection (this article)
  • Step 2 - 12: Coming soon

Today, we start with the first step in any process mining project: The selection of the process that should be analyzed (see below). The other steps will be added in future editions and linked from here.

Process Selection

When you start out with process mining, it is often not so easy to know where to start. Which process should you pick first? And which process might be less suitable for your process mining project?

In a previous article, we identified data availability and process awareness as two key ingredients to judge the suitability of a process for process mining. Read it here to see the detailed break-down and recommendations.

In addition, consider the following tips as well:

  • Agree on the scope. Make sure that everyone has the same understanding of where the process starts and where it ends. Often, people have a different process scope in mind while they are using the same process name (for example, “Is invoicing still part of the purchasing process?” or “Will the pre-operative care be included in the analysis of the surgery process at the hospital?"). All stakeholders should agree on the same process scope.

  • Ensure champion support. Just as important as the data availability is a good support from the team that is responsible for the process. You will need access to a domain expert who knows the process well and can answer questions during your analysis. Without the support of a good champion, you will hit a wall of questions very quickly. Process mining does not happen in a vacuum and an unavailable project sponsor who wants a “surprise me” analysis is a red flag. You also need the support of the process manager in defining the main analysis goals for the process mining project.

  • Keep an eye on improvement potential. If you need to choose a process among multiple good candidates, pick the process that is most relevant and has the most improvement potential. Unless you just want to play around for learning purposes, there must be an interest from the business in the results of your process mining analysis. You can either assess the improvement potential with a classical business case analysis or base the decision on the gut feeling and anecdotal evidence from the process experts. If you still have a tie between multiple processes, go for the one with the highest volume (for example, based on the number of cases that are processed).

Have you picked your process? Then you can move to the next step: Making your project plan.

Process Mining in Healthcare

In last week’s Process Mining Café, we talked about process mining in healthcare with Luise Pufahl, a postdoctoral researcher at TU Berlin in Germany, and Fran Batchelor, a nursing informatics specialist at UW Health in the United States. You can now watch the recording here.

When you apply process mining to a healthcare process then at first everything seems to be very clear: The patient ID should be the case ID, the steps are the diagnosis, treatment, or scheduling activities that took place, and the timestamps are the date and time when the activity happened. However, there are many challenges that make things more difficult in practice.

We discussed the specific challenges of process mining in healthcare along the phases of a typical process mining project.

1. Scoping

First, you need to answer the question where does the process start and where does it end? Simply taking the patient ID as the case ID means that the scope spans the lifetime of the patient. Usually, this is too big and you want to limit the analysis to a smaller scope like a surgery. Another way to focus the analysis is to select a subset of activities, for example, based on the medical guidelines for a specific diagnosis and treatment pathway.

2. Extracting and preparing the data

During the data preparation, often different data sources need to be merged to get all the information that is needed. In this phase, understanding the data and dealing with data quality issues are the biggest problems. For example, there can often be data quality problems if the data is manually recorded. As more data is collected automatically (also by medical devices), the availability and quality of the data improves while data privacy concerns become more important as well.

3. Dealing with complexity

Once you import your data set into Disco, you need to deal with the complexity of the process even more than you would for most other processes. For example, it can easily happen that a data set with 1000 cases has 1000 variants, because every patient follows a unique path. The grouping of cases, leaving out details, activity aggregation, but also unfolding can help to get the data set to the right level for the analysis.

4. Analyzing and communicating the results

To interpret the analysis results correctly, domain knowledge is very important. The process visualizations that can be produced with process mining are more complicated than the manual Visio models that are often traditionally created, because they show all the unexpected flows, exceptions, and inefficiencies. However, in contrast to the manual models they show the actual flow of the process and help a lot in the communication with the medical staff.

Thanks again to Luise and Fran, and to all of you, for joining us!

Here are the links that we mentioned during the session: