This year’s BPM conference took place from 26 to 30 August in Beijing, China. Unfortunately, we could not make it this year. That does not stop us from giving you our annual recap blog post of process mining at BPM 2013, though.
To make sure you can keep up with the news on the process mining research front, we again hunted down the papers that were not made publicly available by the authors yet. They all were kind enough to upload their author version for you. For the main conference papers, even the presentations are available. Enjoy!
Papers at the main conference
Each year, the BPM conference gets hundreds of submissions, and only around 20 papers are accepted for the competitive main track. This year, three out of eight sessions were dedicated to process mining. You find a list of all the papers with pointers to the PDF author version and the slides that were presented below.
Session 1: Process Mining
Session 4: Conformance Checking
Session 8: Process Mining
Papers at the BPI Workshop
The BPI workshop is traditionally the place were early work on process mining topics is presented and discussed. This year, six papers were accepted and you can read them following the pointers below:
Results of the BPI Challenge
After the presentations at the BPI workshop, the winner of the BPI Challenge 2013 was announced. The award goes to Chang Jae Kang, Young Sik Kang, Yeong Shin Lee, Seonkyu Noh, Hyeong Cheol Kim, Woo Cheol Lim, Juhee Kim and Regina Hong, a team from Myongji University in Seoul, Korea.
You can read more about the BPI Challenge award and find pointers to all twelve submissions here.
Annual meeting of the IEEE Task Force on Process Mining
The IEEE Task Force on Process Mining traditionally hold their annual meeting together with the BPM conference, at the end of the BPI workshop.
You can read the minutes and download the slides of this year’s task force meeting.
At the end of yesterday’s BPI Workshop, the winner of the BPI Challenge 2013 was announced. The award goes to Chang Jae Kang, Young Sik Kang, Yeong Shin Lee, Seonkyu Noh, Hyeong Cheol Kim, Woo Cheol Lim, Juhee Kim and Regina Hong, a team from Myongji University in Seoul, Korea. Congratulations to the winners also from us here at Fluxicon!
From the official announcement:
The jury particularly liked the analysis and found the reasoning style easy to follow. The authors made a point of clearly defining their interpretations and arguing for their assumptions. The graphs were mostly well-explained. Furthermore, the report shows a good mix of the use of process mining tools and statistical analysis tools.
The BPI Challenge, which was held for the third time this year, is the most prestigious and high-profile competition for process mining and related process analytics professionals. As proud supporters and sponsors of the challenge, we here at Fluxicon wanted to create a special award trophy for the winner, signifying this achievement. The award, which you can see above, was hand-crafted by Felix Günther, after an original concept and design. It is made from a single branch of a plum tree, which symbolizes the “log” that was analyzed in the challenge. The copper inlay stands for the precious information that was mined from the log.
We would like to thank everyone who participated in the BPI Challenge. Winning this competition is of course a great achievement. However, as with the Olympics, the process of participation alone should make this challenge worthwhile, and it also shows your support of the process mining community. We are of course happy to see so many participating teams using Disco for their analysis, thanks a lot for that!
Last but not least, we would like to extend our thanks to the organizers and judges of the BPI Challenge, especially Boudewijn van Dongen, for a great job, and a great collaboration.
If you are curious how the various participants approached the challenge, and what they found, we have listed all submissions here for your convenience.
- Winner: C. J. Kang, Y. S. Kang, Y. S. Lee, S. Noh, H. C. Kim, W. C. Lim, J. Kim and R. Hong (Myongji University, Korea)
- A. Bautista, S. Akbar, A. Alvarez, T. Metzger and M. Reaves (CKM Advisors, USA)
- M. Arias and E. Rojas (Pontificia Universidad Católica de Chile, Chile)
- S. vanden Broucke, J. Vanthienen and B. Baesens (KU Leuven, Belgium and University of Southampton, UK)
- E. Dudok and P. van den Brand (Perceptive, The Netherlands)
- F. van Geffen and R. Niks (Rabobank, The Netherlands and O&I Management Consultants, The Netherlands)
- J. Hansen (ChangeGroup, Denmark)
- J. Hevia and C. Saint-Pierre (Pontificia Universidad Católica de Chile, Chile)
- J. Martens (Capgemini, The Netherlands)
- Z. Paszkiewicz and W. Picard (Poznan Unviersity of Economics, Poland)
- S. Radhakrishnan and G. Anantha (SolutioNXT Inc., USA)
- P. Van den Spiegel, L. Dieltjens and L. Blevi (KPMG Advisory, Belgium)
Update: The BPI Challenge submissions have been made available as CEUR Workshop Proceedings, along with a summary by the organizers, which includes a selection of the jury comments for each submission.
The video recordings of the presentations at the bpmNEXT conference have been online for a while already, we just have not gotten around to posting the link yet. We were the first to present at an inhumanly 8:00 AM in the morning of the first day and even won the Best in Show award at the end of the conference.
We are particularly proud on this award, because all the other presenters had such fantastic and interesting demos. You can watch our award-winning talk if you click on the picture below.
You need to provide your email address on the conference website to see the recording. But you only have to do it once and then you can watch all the presentations. Make sure to take a look. All of them were really great, so it’s well worth your time.
This is a guest post by Pavlos Delias from the Kavala Institute of Technology in Greece, who shared a summary of his latest process mining case study for you here on our blog.
As we have seen in previous case studies, healthcare processes usually have a high variability in their flows due to the highly customized medical guidelines and the unique path followed by each ￼patient. Therefore, methods to simplify the discovered process flows are needed.
You can read the full scientific article here.
The analyzed Process
The General hospital of Chania is the unique hospital of the prefecture, serving 67,000 citizens. It is a 400 bed hospital providing all types of health services. The management committee of the hospital asked the research team to analyze their emergency department process.
The manager of the emergency department (who is a doctor) described the process verbally as follows:
The Hospital has two Emergency Departments (ED). The first one, ED1, runs 16 hours per day and the second one, ED2, 24 hours per day. Generally, patients that arrive between 08:00 and 23:00 have to pass through registration. Depending on the triage (red cases = extremely important), patients can skip registration and examination at ED1 and are sent directly to ED2.
When patients arrive at the emergency department prior to 23:00, they have to register at the registration office in ED1. The patients will provide information like their name, age, etc., and have to pay 5 euro for the examination. Afterwards, they have to wait at the waiting room. A nurse will ask the patient about their problems and will characterize the level of the triage. The patients that arrive by the ambulance are sent directly to ED2. Furthermore, patients with urgent problems, like, for example, cardiological incidences or serious accidents, receive the highest priority level (red) and are sent directly to ED2.
The process scope at ED2 is twofold. Firstly, patients who enter the emergency department of the hospital after 23:00 will be served by ED2 because ED1 is closed. Secondly, the normal ED2 process treats patients that face serious problems with their health (belonging to the yellow and red scale of triage). When a patient enters the room of diagnosis the nurse will check the temperature, blood pressure, and heartbeat. Then the physician will provide an initial examination. Depending on the level of triage, a patient waits for the lab results at the waiting room or in bed.
When the physician delivers the results of the examination, there are three possible next steps. If the case is serious, the patient is sent to the appropriate department of the hospital. Alternatively, the patient may receive a prescription and is sent back home. The third choice is to decide that the patient will stay at the wards of the emergency department in order to make more lab tests.
The research team drew a flow chart based on this description, which was confirmed as the expected process flow for the emergency department (see figure below).
Figure 1: Emergency department process model (assumed process)
One of the goals was to use the flow chart to perform simulations of the process. Furthermore, we received a sample of data covering 250 patients who visited the emergency department from the hospital information system to compare the actual process with the expected process using process mining techniques.
Process mining results
As a first step, the actual process was discovered using process mining (see pictures of the simplified process below).
Figure 2: The discovered process (100% activities, 0% paths detail – only most important flows are shown)
Figure 3: The discovered process (100% activities, 50% paths)
Several differences could be found by comparing the real process on different levels of detail with the assumed process from Figure 1:
- There are more entry points as well as exit points to the process than the ones illustrated by the flow chart. The team used the “First in case / Last in case” features of Disco to find them. For instance, for few cases ‘Diagnosis’ or ‘Blood Test’ was the initial activity. For other cases, the last activity was ‘Assortment’ or ‘Blood Result’ (or other lab results). While the additional start activities are not so important, the additional exit points require administrative actions.
- There were cases, where patients exit right after Diagnosis — a path which did not exist in the flow chart. Of course, a doctor can diagnose that the sickness is not severe, but letting patients leave without any examinations or lab tests is still an action that could be challenged.
- People may take some lab tests (especially biochemical and enzyme test which take considerable time), leave the hospital and return later. This path is not illustrated in the flow chart.
- There were several cases where prescriptions were made without any examinations. Again, this is possible according to medical guidelines, but it could be investigated.
The focus of the analysis was not check for conformance but to understand the actual process. Recall that the process in Figure 1 is not a rigid prescription of the process but a description of the process by a domain expert.
What became apparent, however, was that the assumed process was not suitable as a basis for simulation, because — due to a lack of alignment with the real process — it would produce faulty results.
As seen in previous healthcare case studies, the actual process exhibits a lot of variation, which can be expected due to the individualistic nature of each patient’s treatment. You can see this variation in the discovered process maps in Figure 2 and Figure 3. Figure 2 is already quite complicated, although it only shows the most important paths in the process. Figure 2 shows 50% of the paths (still not 100%) and the process already looks like spaghetti.
Due to their complexity, these spaghetti diagrams were of little usefulness for the management committee. So, the challenge was to create simpler process maps that could be used to derive insights about the process.
A common technique for more structured processes is to concentrate on the most frequent variants in the process. However, due to the high variation in the process, the most frequent variants would cover only a small percentage of the patients: Out of 84 observed process variants 68 were followed by just one or two patients (see highlighted area in chart below).
Figure 4: 68 out of the 84 variants were followed by just one or two patients
Therefore, the idea was to provide the management team with scenarios based on behavioral clusters of the process. We calculated a similarity measure for traces, applied a simple technique to deal with outliers, and used spectral clustering to get the clusters.
Clustering allowed us to summarize the 84 variants into three, more intuitively explained, process models (see figure below).
Figure 5: Process models for each of the three clusters (100% activities, 0% paths detail – only most important flows are shown)
When comparing the process flows for these three clusters, the following difference can be detected:
- In Cluster (a), the ‘Registration’ step is often skipped. The overall distribution of the triage percentages in the sample was: Green ~34%, Yellow ~57%, and Red ~8%. Cluster (a) has exactly this distribution. However, Green cases (not severe) of this cluster visit the hospital during the night shift. It was surprising that so many patients with Green triage visited the emergency department during the night.
This can be attributed to the economic crisis: Before the crisis, the emergency department in public hospitals in Greece was free. After the crisis, the registration costs 5 Euro. However, during the night, there is no registration at that particular hospital because there is no secretary available. So, poor people with not severe health problems wait until the night to visit the hospital, in order to avoid paying the 5 Euros.
- In Cluster (b), ‘Registration’ is also skipped, but this can be attributed to a higher emergency of cases (much more Red cases than normal). Moreover, this cluster has a higher frequency of lab tests (all patients have blood / biochemical / enzyma tests). Finally, this cluster has a high percentage of patients that enter a clinic rather than just leaving the hospital.
- Cluster (c) is closest to the expected flow (but Yellow cases are over-represented). People get registered, assorted, have some tests, and are forwarded towards the exit via the expected way (after a prescription or a treatment in the ED room).
Why is this important?
In retrospect, we were able to correlate the patients’ clusters with their triage. Since it is quite easy to estimate the statistical distribution for the triage, exploiting the process model of each cluster, it is possible to predict more accurately the workload per activity, create a better resource allocation plan, etc.
Furthermore, based on the results, we were able to communicate the parameters of operations management to doctors, who usually claim that medical guidelines cannot allow for operational optimization.
Finally, we could provide interesting insights, such as that some patients with not severe illnesses came to the hospital at night to avoid the registration costs of 5 Euro, which can be attributed to the economic crisis.
++ Update: These webinars are over but you can watch the video recordings on YouTube! ++
More than 1500 people have already watched the new process mining movie since it was published last week.
The movie explains what process mining is in less than 2 minutes. But how exactly do you get started if you want to apply process mining for your own process? What kind of questions can you answer with process mining? And what are the data requirements?
In our new webinar, we show you how you can start analyzing your own process with Disco in less than five minutes. After the webinar, you will know the data requirements for process mining by heart, and you will be able to identify suitable use cases.
After our webinar, all participants will receive a complimentary Disco evaluation license for one week, so that you can put your new skills to use right away, on your own process.
Here is an overview about the topics we will cover:
- What is process mining, and why do I need it?
- How does it work?
- Process mining with Disco
- Case studies
When is it, and how do I sign up?
We offer this webinar on Wednesday 10 July in three different languages. You can sign up for the German, Dutch, or English edition of the webinar here:
At Fluxicon we focus exclusively on process mining, and we are probably the most experienced experts on this topic not working at a university right now. This means that you can ask us anything, and we can help you get started in the best possible way.
See you at the webinar!
About the presenter
Anne Rozinat is a co-founder of Fluxicon and obtained her PhD cum laude in the process mining group of Prof. Wil van der Aalst at Eindhoven University of Technology. She has ten years of experience in developing and applying process mining and helped shape Disco to fit the requirements of professional users.
Towards the end of last month’s process mining camp, I found myself in a small group, and the conversation circled in on the question: “What is the number one obstacle holding back Process Mining?” A number of topics were brought up, from the difficulties of getting data in some settings, to organizational barriers. I don’t think there is a single best answer, but my personal favourite would still be: Most people don’t even know that Process Mining exists, or what it is exactly.
Spreading the word about Process Mining is a goal that is near and dear to our hearts here at Fluxicon. We have teamed up with the Process Mining Group of Wil van der Aalst at Eindhoven University of Technology, and we have produced a short video clip. Our video introduces the basics of Process Mining, and why you would want to use it. We wanted to make it understandable and comprehensive, but also short and sweet.
Have a look, and see whether we succeeded:
(Click here to view this video on YouTube)
We would like to thank Wil and his group for a great collaboration, and of course our very smart and talented friends at 908video in Berlin, who did the actual work and heavy lifting!
We hope that you like our video, and that it will be a conversation starter and a way to share the magic of Process Mining with your friends and colleagues. Let us know what you think about it right below in the comments!
Are you eager to compare your skills to that of other process miners? Do you feel like sinking your teeth into an unknown data set, test your secret weapons, and see what you can make of it?
Then the Business Process Intelligence (BPI) Challenge 2013, which has just opened, is for you! The BPI Challenge is an annual process mining competition, which takes place this year for the third time.
As Boudewijn explained in an interview last year, the trigger for the BPI Challenge was the lack of publicly available real-life data sets that could be used by process mining researchers: What do you do if you want to try out process mining, but don’t have any data yourself?
With the BPI Challenge, one real-life data set is made available for both researchers and practitioners each year. In 2011, a difficult healthcare data set was provided. In 2012, the data set was from a loan application process at a financial institution. This year, Volvo IT Belgium provided a log with events from an incident and problem management system called VINST.
The format for the BPI Challenge is an open competition, where everybody can participate. You can use any tools you want. The results need to be documented in Word or LaTeX and submitted per email by:
Deadline for submissions: July 12, 2013, 23:59 CET
Why should you participate?
Next to the honor and glory of winning the competition, of course, what is a better way to learn about process mining than to actually analyze a real-world data set? While it is possible to develop entirely new approaches to analyze the data set, the focus is on the application of process mining techniques to achieve results that are relevant from a business perspective.
Are you a researcher? This is the chance to showcase your research and test the benefit of applying it in practice.
Are you a practitioner? Last year’s winners were a data analytics team from the New York-based consultancy CKM Advisors, and they won even though they were new to the topic! The jury particularly highlighted their successful translation of analysis results into business level results and recommendations. Take a look at the submissions from last year if you would like to get an idea of how others have approached this challenge.
This year’s competition is very interesting because the data is exceptionally well-documented, and clear problems and questions have been formulated by the process owner. Head over to the BPI Challenge website now and take a look!
Analyzing the BPI Challenge data in Disco
Do you want to analyze the BPI Challenge data with Disco? Like last year, we have prepared a special Disco workspace with the challenge data, which you can fully analyze with Disco, even if you don’t own a license. Just follow these three steps:
- Download and install the demo version of Disco from the website here
- Download this BPI Challenge project file to your hard disk
- Open the saved project file in Disco
After opening the project file, you will find three data sets, for incidents, open problems, and closed problems as shown in the screenshot above.
Good luck with the challenge!
Fluxicon is a proud official sponsor of the BPI Challenge 2013. We are strong supporters of academic research and education in process mining, notably through our Academic Initiative, and our mission is to translate leading process mining research into friendly and powerful tools for professionals. We thank the organizers of the challenge for providing this bridge between academia and industry, and are delighted to be on board!
Process Mining Camp 2013 is already tomorrow! So, what would be a better warm-up than another fireside chat with one of our practice speakers at camp.
Previously, we have already spoken with Tijn van Heijden, Walter Vanherle, Lalit Wangikar, and Youri Soons. Today, you can read the fireside chat with our fifth practice speaker Philipp Horn below.
Philipp Horn has worked in the Business Intelligence area of the Purchasing department of Volkswagen, Germany, for more than 5 years.
He is a front runner in adopting new techniques to understand and improve processes and will talk about his process mining experiences at camp.
Interview with Philipp
Anne: Someone recently told me that organizations are getting ready for process mining, because they have now understood the importance of process thinking and started to develop a culture around processes. Do you think that is true?
Philipp: I would agree, because if you want to continue improving productivity, you need to get to the process level eventually. You might start by improving the IT systems to gain quick wins, but eventually the further improvement opportunities are lying in the processes themselves.
Anne: Are there any special challenges that one is facing when improving high-volume processes at a large scale?
Philipp: I have to say that due to the enormous complexity one has to be very careful to not oversimplify. There is a risk with managers misinterpreting the results of an analysis if they are not guided by someone who has the complete overview. For example, in a discovered process model it is easy to say that this process should be simpler here and there, but often there are good reasons for these exceptions today. To distinguish what is necessary and what could be actually improved requires both process knowledge and domain expertise on a detailed level.
Anne: Thanks, Philipp! I absolutely agree. Often process mining results can be interpreted in multiple ways, and there lies a big responsibility for the analyst to take all the context information into account and to draw the right conclusions. We are looking forward to hearing more from you at camp!
Would you like to hear more from Philipp about his experiences? Are you interested in sharing first-hand knowledge with fellow process miners? Register now to reserve your seat at Process Mining Camp on 28 May in Eindhoven. We only have a handful of tickets left…
As a warm-up for Process Mining Camp, we asked some of the speakers for an up-front interview. Previously, we already spoke with Tijn van Heijden, Walter Vanherle, and Lalit Wangikar. Today, you can read the fireside chat with our fourth practice speaker Youri Soons below.
Youri Soons has been working as an IT auditor for the Dutch National Auditing Service for more than 5 years. Currently, Youri is establishing process mining as a regular auditing tool within the institution.
At camp, you will get his perspective on how process mining helps to gain more assurance.
Interview with Youri
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?
Youri: That was about four years ago, during a presentation of a colleague IT auditor of the Ministry of Infrastructure & Environment. What fascinated me was that with a push of the button it will gain insight into the full mass. This makes it possible to find all the abnormalities in a process, but also derives a lot assurance from the data.
Anne: Right! How would you explain the concept of assurance to a non-auditor? And how does process mining help in gaining more assurance?
Youri: As auditor we are asked to provide assurance about the functioning of a process. For example, because it is required by law or because the customer wants to get a certain degree of assurance on the functioning of his process. It is then up to us to conduct an audit and determine whether we are able to provide that degree of assurance.
Process mining is, moreover, not the means by which you can provide assurance, you have to see it as a tool to provide the required assurance in a more efficient way. It is also not to say that we deliver more assurance than before.
Process mining provides insight on how the process is handled, by whom and when, but still says nothing about the correctness of decisions. You have to combine the results of process mining in a smart way with other research methods.
So, for example, we can determine whether steps are skipped or segregation of duties is broken. As a result, we are able to focus at the files of these exceptions.
Anne: Interesting, so what you are saying is that process mining helps you to see what is going right, and then to only focus on the exceptions?
Youri: That’s right. We always submit the results of the analyses against the intended process. Deviations may in fact mean that incorrect decisions are made. For example, that a subsidy is granted unfairly. And then we are just looking to those files.
Anne: Can you give us a sneak preview of what you will talk about at camp?
Youri: Providing assurance is tied to a number of conditions. I will show how we think you can efficiently deploy process mining in an assurance-based audit approach.
Anne: Thanks, Youri! We are really curious about your presentation!
Would you like to hear more from Youri about his experiences? Are you interested in sharing first-hand knowledge with fellow process miners? Register now to reserve your seat at Process Mining Camp on 28 May in Eindhoven. We only have a strictly limited number of tickets, and they are going fast…
We have finally finished the program for Process Mining Camp, and we are happy to tell you that we have found yet another great practice speaker: Philipp Horn from Volkswagen, Germany! This brings the total tally up to six practice talks — more than three hours of tales from the frontier, from experienced process mining pioneers who live there.
If you have not signed up for camp already, check out the program and sign up now! We have less than 15 seats left, so if you have considered coming we strongly advise you to make your move quickly.
The expedition workshops
The expedition workshops are our little experiment at this year’s camp, and we are really excited about them. Most likely when you hear ‘workshop’, you think of some sort of miniature conference with presentations or exercises — which is quite a different thing than what we have in mind. So, let us explain a bit more about what you can expect.
The initial trigger for the workshops was feedback we received from many people at last year’s camp. They told us how much they loved meeting other process miners, and exchanging their experiences in small, informal groups over coffee and drinks. Especially those campers who were lucky to run into others that shared their same interests or background were enthusiastic about their encounters.
The expedition workshops are designed to make sure that every attendee at this year’s camp will have that experience. Each workshop has a maximum of 10 participants. We are going to ask all attendees to pick their top 3 workshops, and then we will try to match them into groups they are most interested in.
But even more important than that is that we will keep the setting informal: There are no specific rooms, no beamers, and such. Every workshop group will gather, and then find a place in the Zwarte Doos café or outside to settle down for their discussion.
So, please don’t expect a presentation by your workshop host, we specifically asked them to not prepare one. We did, however, make sure that you will have an exceptionally qualified expedition leader in your group to kick off the discussion, and to provide an informed point of view.
Just have a look at this amazing list of process mining experts who will host a workshop at camp:
- Workshop 1: Methodology
Tijn van der Heijden from Deloitte, Netherlands, is the person to talk to about process mining project methodology. He even wrote his Master’s thesis about this topic.
- Workshop 2: Closing The Loop
Who could be better than Lalit Wangikar from CKM Advisors, USA, to discuss about closing the loop. His team won the BPI Challenge 2012 due to their “successful conversion of analysis results in digestible business level results and recommendations”.
- Workshop 3: Business Value
Walter Vanherle from bpi3, Belgium, is no stranger to ROI and business value, with more than 30 years of consulting experience. He will share their own value impact template format to kickstart the discussion.
- Workshop 4: Mining for Auditors
Youri Soons from Auditdienst Rijk, Netherlands, presents a concrete approach about process mining for auditors earlier at camp. Talk shop and compare practices with other auditors in his expedition.
- Workshop 5: IT Service Management
Roy van Wel from the Ministry of Defense, Netherlands, is the perfect host for the IT Service Management workshop. He has recently completed a detailed case study on improving service level controls with process mining at a company.
- Workshop 6: Healthcare Mining
Ronny Mans from TU Eindhoven, Netherlands, is without a doubt the single-most experienced person in the area of healthcare mining. He has written his PhD thesis about the topic and is currently working on process mining in his postdoc project with several hospitals.
- Workshop 7: Setting Up Shop
You probably still remember Frank van Geffen from the Rabobank, Netherlands, from last year’s camp. With several process mining projects inside the Rabobank, he is the expert about setting up shop and can tell a story or two about how to master organizational barriers.
- Workshop 8: Adding Data
Hajo Reijers from the TU Eindhoven / Perceptive, Netherlands, has always liked to combine research and practice. This is why is interested in adding data (quality information, geographic tagging, cost break-downs, you name it) to make process mining more meaningful.
- Workshop 9: Customer Experience
Shaun Moran from Customer Dimension Analytics, Ireland, already applied process mining in the context of customer experience management when he was still at eBay. He has more than 16 years of experience to contribute to the discussion.
- Workshop 10: Forensics and Mining
Thomas Stocker from Freiburg University, Germany, has published several articles on process mining and security. He is the ideal person to join for discussing all kinds of ideas to connect forensics and mining.
- Workshop 11: Social Mining
Alberto Manuel from Process Sphere, Portugal, is one of the most forward-looking and opinionated BPM experts I know. In the social mining workshop he is ready to discuss the importance of social network analysis to get to the bottom of organizational change.
- Workshop 12: Industry Meets Academia
Arthur ter Hofstede from Queensland University of Technology, Australia, is used to connecting research to practice by way of their QUT business courses, consulting and research projects. Discuss with him how to make industry meets academia cooperations a success.
- Workshop 13: Open Source Development
Boudewijn van Dongen from TU Eindhoven, Netherlands, is the mastermind behind ProM and the best person to discuss about all things open source development for process mining. He also initiated the main process mining competition, the BPI Challenge.
- Workshop 14: Standardizing Log Data
Eric Verbeek from TU Eindhoven, Netherlands, is the project lead of ProM, and with the current IEEE accredidation of XES deep into standardizing log data. Discuss what features a log standard needs, directly with the organizer of the XES standard working group.
Regardless of which expedition workshop you are going to attend, you will be in great company. You will get the chance to really connect to your expedition host and the other campers in your group, and get direct access to their vast experience. Dive deep into your favorite process mining topic, participate in a relaxed and open discussion, and make new friends!
Sign up to camp now to choose your three favorite workshop topics.