Wil van der Aalst at Process Mining Camp 2018

Process Mining Camp is just one week away (see an overview of the speakers here) and there are just a few tickets left. So, if you want to come, you should reserve your seat now!

To get ready for this years camp, we have started to release the videos from last year. If you have missed them before, you can still watch the videos of Fran Batchelor from UW Health, Niyi Ogunbiyi from Deutsche Bank, Dinesh Das from Microsoft, Wim Kouwenhoven from the City of Amsterdam, Olga Gazina from Euroclear, and Marc Tollens from KLM.

The final speaker at Process Mining Camp 2018 was Wil van der Aalst, the founding father of process mining. In his closing keynote, Wil talked about the updated skill set that process and data scientists need today. Since process mining research was starting up in Eindhoven in the late 90s, the availability of suitable data has increased tremendously, which makes it even more important that this data can and will be used in an appropriate and responsible manner.

This requires dedicated capabilities from the process miner in each stage of the analysis pipeline: Processing and analyzing data, being responsible about the effects on people, and on business models. When you look for people who are skilled in all of these technical areas, as well as in soft skills like communication and ethics, you start looking for (as they would say in the Netherlands) a sheep with 5 legs, or something that is very rare. Becoming a data scientist requires a lot of effort to learn all the skills that are needed to live up to these high expectations.

As ambassadors of process mining, we also have the responsibility to use the right terms. Wil sees a clear a distinction between Artificial Intelligence (AI), machine learning, and data mining. At the same time, one could argue that process mining is data mining, but the underlying techniques are very different. So, saying that process mining is part of data mining, or AI, doesnt make any sense.

There are incredible expectations around AI and Big Data, which is very dangerous as we have seen in past AI winters. We should be careful not to overpromise and try to be realistic. The incredible successes of machine learning techniques like deep learning are, for example, still limited to very specific fields.

Some in the media and big technology companies use terms like Artificial Intelligence, Machine Learning, and Deep Learning interchangeably. They might argue that you dont need process mining as you can just put an event log into a deep neural network and a process model will come out. There is, however, not one deep learning algorithm that can discover a process model. Instead, when we look at process mining it combines the fields and methods of process science and data science. This makes it even more challenging for us to cover all required skills.

But do you, as a professional, need to know how a car works internally in order to drive it? It depends on what you want to accomplish. For example, if you need to drive fast around the Nurburg Ring, it can be very useful. Also, if you need to select a car then it would certainly be useful to know about its internals. Process mining is a relatively young technology. Therefore, it is useful to know how it works in order to select the right tool, and to use it to maximum effect.

So what kind of skills do you need as a process miner? You need to be able to extract and clean the data, spend time on the analysis, and interpret the results. This is not easy. All the involved parties need to invest the time to determine what the process maps actually mean, so that they can really trust their interpretation. The sheep with five legs would be the ideal process miner, but in most cases this is not realistic.

Traditionally, you will often rely on collaboration between a data-driven expert and a business/domain-driven expert. However, you can also think about more hybrid process mining profiles. Some experts can integrate technological skills into their domain knowledge, while other data scientists can be process mining experts which are especially skilled to perform specific types of analysis in a particular domain.

Do you want to know what kind of process miner you could become? Watch Wil's talk now!


If you can't attend Process Mining Camp this year, you should sign up for the Camp mailing list to receive the presentations and video recordings afterwards.

Process Mining at KLM — Process Mining Camp 2018

In only two weeks we will see each other at this year's Process Mining Camp (see an overview of the speakers here). If you are not registered yet, get one of the last tickets here now!

To get ready for this years camp, we have started to release the videos from last year. If you have missed them before, you can still watch the videos of Fran Batchelor from UW Health, Niyi Ogunbiyi from Deutsche Bank, Dinesh Das from Microsoft, Wim Kouwenhoven from the City of Amsterdam, and Olga Gazina from Euroclear.

The sixth speaker at Process Mining Camp 2018 was Marc Tollens, a digital product owner at Air France KLM. In order to compete in the aviation market, KLM focuses on providing an excellent customer experience. They adopted the agile methodology to be able to reduce the time to introduce new touch points in the traveler's journey. The performance of the agile teams is crucial to get the most out of each sprint.

As a Sunday afternoon project, Marc collected data from Jira, a project management software for (agile) software development, to see how process mining could be applied to help the teams learn from each other. Surprisingly, the flow of each team was quite different.

Marc started comparing the flows of the three teams to identify key differences in behavior and the resulting effects. In this way he could see if a team was able to deliver what they promised and whether they started testing too early or too late. He shared his observations with the teams during the retrospective and returned for the next sprint to see how the improvement worked out.

Do you want to see what happened after the retrospective? Watch Marc's talk now!


If you can't attend Process Mining Camp this year, you should sign up for the Camp mailing list to receive the presentations and video recordings afterwards.

Process Mining at Euroclear — Process Mining Camp 2018

This year's Process Mining Camp is just three weeks away. If you have not registered yet, don't wait and reserve your ticket here now!

To get us all in the right mood for camp, we have started to release the videos from last year. If you have missed them before, you can still watch the videos of Fran Batchelor (UW Health), Niyi Ogunbiyi (Deutsche Bank), Dinesh Das (Microsoft), and Wim Kouwenhoven (City of Amsterdam).

The fifth talk at Process Mining Camp was given by Olga Gazina and Daniel Cathala from Euroclear. As a data analyst at the internal audit department Olga helped Daniel, IT Manager, to make his life at the end of the year a bit easier by using process mining to identify key risks.

She applied process mining to the process from development to release at the Component and Data Management IT division. It looks like a simple process at first, but Daniel explains that it becomes increasingly complex when considering that multiple configurations and versions are developed, tested and released. It becomes even more complex as the projects affecting these releases are running in parallel. And on top of that, each project often impacts multiple versions and releases.

After Olga obtained the data for this process, she quickly realized that she had many candidates for the caseID, timestamp and activity. She had to find a perspective of the process that was on the right level, so that it could be recognized by the process owners. In her talk she takes us through her journey step by step and shows the challenges she encountered in each iteration. In the end, she was able to find the visualization that was hidden in the minds of the business experts.

Do you want to see how Olga was able to find the right perspective in her spaghetti process? Watch Olga's talk now!


If you can't attend Process Mining Camp this year, you should sign up for the Camp mailing list to receive the presentations and video recordings afterwards.

Process Mining at the City of Amsterdam — Process Mining Camp 2018

Process Mining Camp is coming up in just under a month and tickets are going fast! Take a look at the speakers and workshops and get your ticket here to join the event.

To get ready for this years camp, we have started to release the videos from last year. If you have missed them before, you can still watch the videos of Fran Batchelor (UW Health), Niyi Ogunbiyi (Deutsche Bank), and Dinesh Das (Microsoft).

The fourth speaker at Process Mining Camp 2018 was Wim Kouwenhoven from the City of Amsterdam. Amsterdam is well-known as the capital of the Netherlands and the City of Amsterdam is the municipality defining and governing local policies. Wim is a program manager responsible for improving and controlling the financial function.

A new way of doing things requires a different approach. While introducing process mining they used a five-step approach:

Step 1: Awareness

Introducing process mining is a little bit different in every organization. You need to fit something new to the context, or even create the context. At the City of Amsterdam, the key stakeholders in the financial and process improvement department were invited to join a workshop to learn what process mining is and to discuss what it could do for Amsterdam.

Step 2: Learn

As Wim put it, at the City of Amsterdam they are very good at thinking about something and creating plans, thinking about it a bit more, and then redesigning the plan and talking about it a bit more. So, they deliberately created a very small plan to quickly start experimenting with process mining in small pilot. The scope of the initial project was to analyze the Purchase-to-Pay process for one department covering four teams. As a result, they were able show that they were able to answer five key questions and got appetite for more.

Step 3: Plan

During the learning phase they only planned for the goals and approach of the pilot, without carving the objectives for the whole organization in stone. As the appetite was growing, more stakeholders were involved to plan for a broader adoption of process mining. While there was interest in process mining in the broader organization, they decided to keep focusing on making process mining a success in their financial department.

Step 4: Act

After the planning they started to strengthen the commitment. The director for the financial department took ownership and created time and support for the employees, team leaders, managers and directors. They started to develop the process mining capability by organizing training sessions for the teams and internal audit. After the training, they applied process mining in practice by deepening their analysis of the pilot by looking at e-invoicing, deleted invoices, analyzing the process by supplier, looking at new opportunities for audit, etc. As a result, the lead time for invoices was decreased by 8 days by preventing rework and by making the approval process more efficient. Even more important, they could further strengthen the commitment by convincing the stakeholders of the value.

Step 5: Act again

After convincing the stakeholders of the value you need to consolidate the success by acting again. Therefore, a team of process mining analysts was created to be able to meet the demand and sustain the success. Furthermore, new experiments were started to see how process mining could be used in three audits in 2018.

For Wim process mining is a discipline, not only a tool. Therefore, you need to find the right balance between the process, the tools and the people. Firstly, if you focus too much on your own results you will limit the learning experience organization wide. Secondly, the more pressure we put on others the less results will be achieved for the organization as a whole. Finally, you need to inspire others and let process mining grow.

Do you want to learn from the best practices from the City of Amsterdam and grow your own processes? Watch Wim's talk now!


If you can't attend Process Mining Camp this year, you should sign up for the Camp mailing list to receive the presentations and video recordings afterwards.

Process Mining at Microsoft — Process Mining Camp 2018

Process Mining Camp is just five weeks away! Take a look at the speakers and workshops and get your ticket here.

While we are all waiting for camp day to roll around, we are releasing the videos from last years camp. If you have missed them before, you can still watch the videos of Fran Batchelor from UW Health and Niyi Ogunbiyi from Deutsche Bank.

The third speaker at Process Mining Camp 2018 was Dinesh Das from Microsoft. Dinesh Das is the Data Science manager in Microsofts Core Services Engineering and Operations organization.

Machine learning and cognitive solutions give opportunities to reimagine digital processes every day. This goes beyond translating the process mining insights into improvements and into controlling the processes in real-time and being able to act on this with advanced analytics on future scenarios.

Dinesh sees process mining as a silver bullet to achieve this and he shared his learnings and experiences based on the proof of concept on the global trade process. This process from order to delivery is a collaboration between Microsoft and the distribution partners in the supply chain. Data of each transaction was captured and process mining was applied to understand the process and capture the business rules (for example setting the benchmark for the service level agreement). These business rules can then be operationalized as continuous measure fulfillment and create triggers to act using machine learning and AI.

Using the process mining insight, the main variants are translated into Visio process maps for monitoring. The tracking of the performance of this process happens in real-time to see when cases become too late. The next step is to predict in what situations cases are too late and to find alternative routes.

As an example, Dinesh showed how machine learning could be used in this scenario. A TradeChatBot was developed based on machine learning to answer questions about the process. Dinesh showed a demo of the bot that was able to answer questions about the process by chat interactions. For example: “Which cases need to be handled today or require special care as they are expected to be too late?". In addition to the insights from the monitoring business rules, the bot was also able to answer questions about the expected sequences of particular cases. In order for the bot to answer these questions, the result of the process mining analysis was used as a basis for machine learning.

Do you want to know more about the combination of process mining and machine learning? Watch Dinesh's talk now!


If you can't attend Process Mining Camp this year, you should sign up for the Camp mailing list to receive the presentations and video recordings afterwards.