Sixth International Business Process Intelligence Challenge (BPIC’16)

In this challenge, we provide participants with a real-life event log, and we ask them to analyze these data using whatever techniques available, focusing on one or more of the process owner's questions or proving other unique insights into the process captured in the event log.

We strongly encourage people to use any tools, techniques, methods at their disposal. There is no need to restrict to open-source tools, and proprietary tools as well as techniques developed or implemented specifically for this challenge are welcome.

The winner will be announced at the Workshop on September 19th 2016.

GRADIENT ECM is providing free Minit licenses for participants of the Business Processing Intelligence Challenge 2016. Minit is an innovative software for automated discovery, analysis, auditing and optimization of business processes. Special licenses of the process mining tool include new functionality from version 2. To get expert answers to questions regarding the use of Minit please visit the BPI Challenge 2016 Forum. Licenses are valid until 1st August 2016.

To apply for a free license please send an email to BPI2016@gradientecm.com.

UWV (Employee Insurance Agency) is a Dutch autonomous administrative authority (ZBO) and is commissioned by the Ministry of Social Affairs and Employment (SZW) to implement employee insurances and provide labour market and data services in the Netherlands.

The Dutch employee insurances are provided for via laws such as the WW (Unemployment Insurance Act), the WIA (Work and Income according to Labour Capacity Act, which contains the IVA (Full Invalidity Benefit Regulations), WGA (Return to Work (Partially Disabled) Regulations), the Wajong (Disablement Assistance Act for Handicapped Young Persons), the WAO (Invalidity Insurance Act), the WAZ (Self-employed Persons Disablement Benefits Act), the Wazo (Work and Care Act) and the Sickness Benefits Act.

The data in this collection pertains to customer contacts over a period of 8 months and UWV is looking for insights into their customers' journeys. The data is focused on customers in the WW (unemployment benefits) process.

Data has been collected from several different sources, namely:

1. Clickdata from the site www.werk.nl collected from visitors that were not logged in,
2. Clickdata from the customer specific part of the site www.werk.nl (a link is made with the customer that logged in),
3. Werkmap Message data, showing when customers contacted the UWV through a digital channel,
4. Call data from the call center, showing when customers contacted the call center by phone, and
5. Complaint data showing when customers complained.

All data is accompanied by data fields with anonymized information about the customer as well as data about the site visited or the contents of the call and/or complaint. The texts in the dataset are provided in both Dutch and English where applicable. URL's are included based on the structure of the site during the period the data has been collected.

UWV is interested in insights on how their channels are being used, when customers move from one contact channel to the next and why and if there are clear customer profiles to be identified in the behavioral data. Furthermore, recommendations are sought on how to serve customers without the need to change the contact channel.

There are five different data files available. The entire collection is available from 10.4121/uuid:360795c8-1dd6-4a5b-a443-185001076eab. Please use this DOI in any reference to the collection as a whole. This collection consists of five different files:

1. Click-data for the customers that are not logged in to the website (1.09 GB in CSV format / 157 MB zipped) 10.4121/uuid:9b99a146-51b5-48df-aa70-288a76c82ec4. Please use this DOI in any reference to the dataset.
2. Click-data for the customers that are logged in to the website (1.06 GB in CSV format / 147 MB zipped) 10.4121/uuid:01345ac4-7d1d-426e-92b8-24933a079412. Please use this DOI in any reference to the dataset.
3. Questions asked by customers (30.7 MB in CSV format) 10.4121/uuid:2b02709f-9a84-4538-a76a-eb002eacf8d1. Please use this DOI in any reference to the dataset.
4. Messages sent by customers (17.8 MB in CSV format) 10.4121/uuid:c3f3ba2d-e81e-4274-87c7-882fa1dbab0d. Please use this DOI in any reference to the dataset.
5. Complaints filed by customers (57 kB in CSV format) 10.4121/uuid:e30ba0c8-0039-4835-a493-6e3aa2301d3f. Please use this DOI in any reference to the dataset.

An explanation of the various fields used in the CSV files can be found in the data dictionary here.

UWV is interested in improving the customer journey. The overall aim of UWV is to assist customers in finding a suitable job within the required time frame and to assist their customers in the process of finding one.

To assist people in this process, the “Werkmap” (workfolder) is an instrument used to track that customers' legal obligations, e.g. do they apply for enough jobs etc. The site www.werk.nl collects open positions and allows customers to find suitable jobs. Customers can log into the site (but don't have to) and they can find positions as well as answers to frequently asked questions or messages from UWV. If a customer cannot find the answer s/he is looking for on the site, s/he can contact UWV through the contact center (by phone) and occasionally, a customer will file a complaint.

Of course, the site is the cheapest channel for UWV to connect with their customers, but it is also the fastest way for customers to find answers. Next, the werkmap messages, the call center questions and finally the complaints are more expensive and slower channels of contact. One of the challenges for UWV is therefore to answer customers' questions through the cheapest and fastest channel.

During the challenge this year, participants get the opportunity to ask questions to the process owner through the ProM Forum. These questions should not be technical in nature, but about the underlying processes etc. The forum is monitored by both the process owner and staff from TU/e.

In particular, UWV is interested in the way both the site www.werk.nl and the Werkmap are used. Any insights into typical usage patterns across the various channels are therefore interesting, but there are some specific questions:

1. Are there clear distinct usage patterns of the website to be recognized? In particular, insights into the way various customer demographics use the website and the Werkmap pages of the website are of interest.
2. Do the usage patterns of the website by customers change over time? Do customers visit different pages when they start using the website versus when they have been using the website for some time? How does the usage change over time?
3. When is there a transition from the website to a more expensive channel, such as sending a Werkmap message, contacting the call center or filing a complaint? Is there a way to predict and possibly prevent these transitions?
4. Does the behavior of the customers change after they have send a Werkmap message, made a phone call or filed a complaint? Are customers more likely to use these channels again after they have used them for the first time? What is the customer behavior on the site after customers have been in contact through the Werkmap or by phone?
5. Is there any specific customer behavior that directly leads to complaints?
6. Finally, we challenge the creative minds, to surprise UWV with new insights on the provided data to help improve the experiences of our customers when using the website.

Just like last year, the challenge is split into two separate challenges. The first challenge is specifically targeting researchers and professionals in the area of business process intelligence, where the second challenge is targeting students (Bachelor, Master and PhD Students).

We received the following submissions through EasyChair at https://www.easychair.org/conferences/?conf=bpic2016.

• Identification of Distinct Usage Patterns and Prediction of Customer Behavior by Sharam Dadashnia, Tim Niesen, Philip Hake, Peter Fettke, Nijat Mehdiyev and Joerg Evermann
• Exploring different aspects of users behaviours in the Dutch autonomous administrative authority through process cubes by Amin Jalali
• Marking up the right tree: understanding the customer process at UWV by Ube van der Ham
• Analyzing customer interactions at the Dutch Employee Insurance Agency by Gert Janssenswillen, Mathijs Creemers, Toon Jouck, Niels Martin and Marijke Swennen
• BPI Challenge 2016: Usage Analytics using Process Mining - Key Finding for the Dutch Employee Insurance Agency by Nour Assy and Farideh Heidari

The winners of the challenge will be invited to receive an award during the workshop in Rio de Janeiro. This year's BPI Challenge is sponsored by Minit and they are kindly offering the cost of the flight to Rio for the winner of the BPI Challenge to be in Rio when receiving the award.