Time Capsule — Nicholas Hartman at Process Mining Camp 2014

To celebrate our brand-new home for camp talks we are releasing the talks from Process Mining Camp 2013 and 2014 for the first time. Grab a snack, sit back, and enjoy the journey through time, back to the early stages of our process mining community from six years ago!

Nicholas Hartman at CKM Advisors: Process Mining in IT Service Management (United States)

Nicholas Hartman is the director of CKM Advisors. In his view, one of the great things about the processing mining movement is that it’s focused on solving relevant issues that matter to stakeholders — the process owners (rather than focusing too much on tools).

In contrast to pre-determined BI reports, Nick finds that process mining helps to derive actionable insight for process improvement projects, for example, by identifying bottlenecks. Sometimes, it can even help to prevent cases in the first place — because the most efficient process is one that doesn’t happen at all.

Watch Nick’s talk now!


Stay tuned for this year’s Process Mining Camp on 16 & 17 June!

Time Capsule — Oliver Wildenstein at Process Mining Camp 2014

To celebrate our brand-new home for camp talks we are releasing the talks from Process Mining Camp 2013 and 2014 for the first time. Grab a snack, sit back, and enjoy the journey through time, back to the early stages of our process mining community from six years ago!

Oliver Wildenstein at MLP: Monitoring Outsourced Processes (Germany)

Oliver Wildenstein is an IT process manager at MLP. As in many other IT departments, he works together with external companies who perform supporting IT processes for his organization. With process mining he found a way to monitor these outsourcing providers.

Rather than having to believe the self-reports from the provider, process mining gives him a controlling mechanism for the outsourced process. Because such analyses are usually not foreseen in the initial outsourcing contract, companies often have to pay extra to get access to the data for their own process.

Watch Oliver’s talk now!


Don’t miss this year’s Process Mining Camp and join us on 16 & 17 June!

Time Capsule — John Müller at Process Mining Camp 2014

To celebrate our brand-new home for camp talks we are releasing the talks from Process Mining Camp 2013 and 2014 for the first time. Grab a snack, sit back, and enjoy the journey through time, back to the early stages of our process mining community from six years ago!

John Müller at ING: Customer Journey Mining at ING DIRECT Australia (Netherlands)

John Müller is a data scientist at ING bank. During a project of analyzing website data before the customer calls the help desk, it hit him that this data could be seen as a customer journey process. Just because a website has no specific order in which people have to click did not mean it is not possible to use process mining.

There was a clear start (the login), a clear middle (the switch to the call center) and a clear end (a hopefully satisfied customer hanging up). Analyzing the customer journey data with process mining changed the way questions were asked, because the process mining tool allowed the business user to explore their own process and find their own answers, thus using their domain knowledge to the fullest.

Watch John’s talk now!


Don’t miss this year’s Process Mining Camp and join us on 16 & 17 June!

Case Study: Cost Deployment With Process Mining

At Process Mining Camp 2019, we had the pleasure to hand out the annual Process Miner of the Year award for the fourth time. Our goal with the Process Miner of the Year awards is to highlight process mining initiatives that are inspiring, captivating, and interesting. Projects that demonstrate the power of process mining, and the transformative impact it can have on the way organizations go about their work and get things done. We hope that learning about these great process mining projects will inspire all of you and show newcomers to the field how powerful process mining can be.

We picked the case study from GlaxoSmithKline (GSK) as the winner, because they developed a new approach for cost deployment in manufacturing with process mining. Cost deployment is a method from World Class Manufacturing, where an industrial engineering approach is taken to understand the cost of losses within an organisation (based on 100% of the cost). A key success factor was the involvement of the Subject Matter Experts (SMEs) and the initial segmentation of the data. Kevin Joinson, Director of Data Science & AI CoE at GSK, drove the initiative and received the award at Process Mining Camp 2019. Learn more by reading their case study here.

Congratulations to the team from GSK!


Don’t miss this year’s Process Mining Camp and join us on 16 & 17 June!

Remove Repetitions With Excel

In edition 5 of our series on typical process mining data preparation tasks we showed how you can remove repetitions from your data to create more meaningful variants. We presented a solution that identifies the repetitions in Python. Rens van den Bos from the TU Delft contacted us with another solution that does the same in Excel. Since Excel is going to be an easier data transformation tool for many of you than Python, we want to share his solution with you here as well. Thanks, Rens!

The example that we used to illustrate this transformation is the 2016 BPI Challenge process (see image at the top). The data set consists of the steps that people follow to apply for unemployment benefits. Each step is a click on the website of the unemployment benefit agency.

What you can see in this process map is that there are a lot of self loops (highlighted by the red rectangles in the image). These repetitions come from multiple clicks on the same web page. They can also come from a refresh, an automated redirection, or an internal post back to the same page. So, they are more of a technical nature than an actual repetition of the same process step.

As a result, these repetitions are not meaningful for analyzing the actual customer experience for this process. What is worse, these repetitions also create many more variants than there actually are from a high level process perspective.

So, here is how you can remove these repetitions in Excel rather than in Python as in our original article.

Step 1: Sort the data in Excel

In order to determine if an activity is a repeating activity, the data set needs to be sorted based on the caseID and the timestamp first. In Excel you can perform a ‘custom sort’ and select the columns and the order in which they need to be sorted. Here, we first sort the data based on the caseID and then sort the events in the order of their completion time (see screenshot below).

Step 2: Add column using Excel formula

Then, we determine for each event whether it is a repetition. A repetition occurs when an activity is preceded by the same activity within that case. As in our previous approach, repetitions are not immediately deleted but just marked by a new data attribute that allows us to filter out repetitions in the process mining tool. This way, we preserve the original data.

To detect whether an event in a row is a repeating activity, one needs to look at the previous row and determine if the caseID and activity are the same. This can be translated into an Excel formula as shown in the screenshot below.

Once you apply this formula to the first event in the data set, you will see the value FALSE because the first event is not a repetition yet.

If you now double click on the bottom right corner of the cell with the formula (see the green little square in the lower right corner in the screenshot above), then the formula is automatically applied to all the rows in your data set.

If everything works, the formula is now applied for every event and, for example, the second event in case 8919 is shown as TRUE because it is a repetition of the previous event (see below).

Make sure that you save the resulting file as a CSV file before you import it into Disco, so that the results of the formula will be saved as values that can be read as an attribute value. To do this, use the ‘File -> Save As’ menu function in Excel and choose ‘CSV’ as the File Format in the export step.

To follow the last steps of actually analyzing the data without repetitions, read onwards from Step 3 in the original article here.