Lean Six Sigma and process mining working together
To demonstrate how the two work together, let’s take a look at each of the phases of Lean Six Sigma, and talk about how process mining can help.
Define — what is the problem?
At this stage you figure out things like the problem, team, scope, and timings of the project.
The fit for process mining is obvious here. By ingesting real-time data, you instantly get an objective view of exactly what’s going on in your processes, can define the problem, identify your stakeholders, and depending on your process mining vendor, can even set the scope of your project by saving a selection of just the process variants you want to focus on.
Measure — how big is the problem?
Here you measure the performance of the process as it currently is, and set your KPIs so you know your improvements are actually having a positive impact.
Process mining does all the heavy lifting in terms of measuring and reporting the current performance of the process. Then once you’ve set your KPIs, they can be shared with the team, so it’s easy for everyone to see how process improvements are going.
Analyze — what are the root causes of the problem?
Now you know what you’re hoping to achieve, it’s time to figure out what’s causing your issues in the first place.
There are many ways process mining can help here, and this phase is where the strength of combining both methodologies really comes into play. Process mining perfectly supports the evaluation of hypotheses, which you have created with traditional exercises such as Ishikawa.
But let’s look at one example of Root Cause Analysis, the 5 Whys, in a more detailed way. In the 5-Whys, you start with a problem then ask why 5 times until you get to the root cause. Let’s look at a real example to see how process mining can help.
Problem: NPS score is trending down
- Why? There are more complaints than usual
- Why? Recently more orders are getting delayed
- Why? Manufacturing lead times have become inconsistent
- Why? One supplier has become unreliable
- Why? They are sourcing raw materials from a region that is unstable
In this instance you can use process mining to identify and confirm root causes, completely eliminating guesswork or additional research.
Improve — how can I eliminate the root causes?
Continuing with the example above, you can also identify possible fixes, like switching to different suppliers, amending your lead times, bundling orders differently, or communicating with customers to better manage expectations.
And because you’re figuring this all out in a system you’re already using, the time to implement is significantly less. In many cases you would have to wait a few months for any kind of IT implementation, but with process mining, you can create automations that write back into your source systems and get to work almost immediately or create action lists to efficiently orchestrate and standardize work across systems.
Control — how do I sustainably eliminate the root causes?
Now that you’ve got your improvements in place, you need to make sure the changes stick. Usually this would involve creating quality control plans and statistical process control, but with process mining you can use the KPIs you defined in the Measure phase to keep track of how the process improvements are affecting performance, and set up an alert for if performance drops below a certain level.