Process Mining at Deutsche Bank — Process Mining Camp 2018

Process Mining Camp is coming closer! This year’s camp takes place on 20 & 21 June, so keep these days free in your agenda. The program will be announced shortly and you can sign up at the camp mailing list to be notified as soon as the registration opens.

Meanwhile, we have started to release the videos from last years camp. You can already watch the video of Fran Batchelor from UW Health here. The second speaker at Process Mining Camp 2018 was Niyi Ogunbiyi from Deutsche Bank in the United Kingdom. Niyi is a Six Sigma Master Black Belt in the Chief Regulatory Office at Deutsche Bank.

Niyi started with process mining on a cold winter morning in January 2017, when he received an email from a colleague telling him about process mining. After searching the internet, he started the MOOC and shared his ideas with the team. They also got very excited to see what they would be able to do with it. They started with their proof of concept in October the same year. In his talk, he shared his process mining journey and the five lessons they have learned so far.

1. Be Persistent & Inventive

His first lesson was to be persistent to get the right people on board to secure the required sponsorship and the funds to get started. Also, getting the data can be challenging. Therefore, you need to be inventive and sometimes try to find other ways to get your hands on a dataset to just get started.

2. Be Clear What Process Mining Can & Can’t Do

The second lesson was to understand what process mining can, but also what it cannot do. To figure this out, they needed to take a step back and look at their current approach. Traditionally, process discovery is done by conducting interviews, which can take a lot of time. Additionally, the resulting model does not always reflect the reality. They saw that process mining could contribute to perform these analyses more quickly and with a higher precision. Another benefit was that with process mining they could test their process for conformance more easily on large data sets instead of manually reviewing process conformance manually based on a smaller sample of cases. Nevertheless, they also learned that process mining would not answer all the process-related questions and that domain expertise is required to be able to translate the insights into actions.

3. Find The Right Balance Between Targeted vs. Untargeted Exploration

When performing their analysis, they found that they were initially spending a lot of time on explorative (untargeted) analysis. While this was fun, and while it revealed a few things about the process that they would not have even thought to ask questions about, the insights from these explorations were often difficult to translate into action and were more anecdotal. In order to become more focused in their analysis they developed templates to answer questions that were relevant to their stakeholders. For example, understanding the relations between the lead time and rework and the case variations. This approach helped them to keep focusing on the relevant factors with the biggest impact. Niyi recommends to spend not more than 30% of your time on untargeted, explorative analysis and 70% on targeted, question-focused analysis, which was the third lesson.

4. Relate Analysis Results To Stakeholders’ Pain

Fourthly, in order to make the insights actionable you need to be able to relate them to the stakeholders pains and gains. Ideally, you can relate the analysis results to problems that otherwise keep the process manager up at night. This will really help to make them care about your analysis and they will help you to drive the actual change that needs to happen after the process mining analysis to realize the benefits. But also give them a clear understanding about the overall opportunities to improve and help them to determine if they are working on the right improvement initiatives.

5. Celebrate Your Successes & Cut Your Losses

Finally, they were able to complete the proof of concepts and continue with a number of other projects. Often, when you have completed something you immediately move on to the next. But in order to build resilience, don’t forget to also take a moment to celebrate and pat yourself on the back. Also: Be realistic and cut your losses when things don’t work out or are just too ambitions.

As a next step Niyi and his team are selecting more processes for process mining. For example, they are looking into employee trading to check conformance and the combination of process mining with RPA. Process mining is great to identify which activities would be the best candidate to automate and to estimate the benefits. Finally, they also see great potential for process mining in fraud detection and are experimenting with this.

Do you want to know more about the lessons Niyi learned? Watch Niyi’s talk now!

Christian W. Günther

Christian W. Günther

Product, development, and everything else

Christian creates software which is easy to use, performs great, and is easy on the eyes. He also handles most things design or AV around Fluxicon.