Leveraging Lean Six Sigma Techniques & Process Mining for Root Cause Analysis
Tradition Techniques & Technology Together
Process and Task Mining are powerful tools for extracting and analyzing data to identify process inefficiencies and bottlenecks. There is a perception that this technology alone can fix processes and this work is treated as a technical exercise. However, for most processes, humans are involved, and it is not simply a matter of applying automation to an already leaned out process. Therefore, it is essential to approach them through a broader lens, incorporating principles of Lean Six Sigma and change management to understand manual activities and develop a broader improvement roadmap. Only then, by combining these insights derived from technology along with traditional Lean Six Sigma techniques, organizations can significantly enhance the effectiveness of their root cause analysis efforts, by driving sustainable process improvement and performance optimization.
While every process and improvement project is different, below are 3 examples of leveraging these pre-existing frameworks to get the most value out of these tools.
Failure Mode and Effects Analysis (FMEA)
Failure Mode and Effects Analysis (FMEA) is a systematic approach used to identify potential failure modes within a process, assess their impact, and prioritize corrective actions. By integrating process mining outputs into FMEA, organizations can gain deeper insights into process behavior and performance, thereby enhancing the accuracy of risk assessment and mitigation strategies. While some of this could be calculated and derived via technical means, the process of doing this with key stakeholders brings non-system and insights into the conversation.
Example:
A manufacturing company is experiencing a high defect rate in a specific production line. By analyzing process mining data, the team identifies instances of prolonged activity duration as a significant contributor to defects. Integrating this insight into FMEA, the team then prioritizes communication of completion at each step and prioritization of aging orders. Combining these technical insights with experts would allow for further conversations around communication challenges, planned production schedule and prioritization of work which would not be included in the technical analysis.
Y = f(X) Methodology
The Y = f(X) methodology, central to Six Sigma principles, emphasizes the relationship between process inputs (X) and outputs (Y). Process mining provides a wealth of data on process inputs, outputs, and their inter-dependencies, enabling organizations to apply Y = f(X) analysis more comprehensively to identify critical factors impacting process performance.
Example:
In a service-oriented function, customer satisfaction (Y) is a key output metric influenced by various process inputs such as response time, accuracy, and communication quality. Process mining analysis reveals that delays in responding to customer inquiries or inaccurate responses are correlated with lower satisfaction scores. Applying Y = f(X), the organization identifies response time as a critical input factor and then works with the impacted team to implement process changes to streamline customer communication channels, resulting in improved satisfaction levels.
Pareto Analysis
Pareto Analysis, based on the Pareto Principle (80/20 rule), focuses on identifying the most significant factors contributing to a problem. By integrating process mining data into Pareto Analysis, organizations can prioritize root causes more effectively, directing resources towards addressing the most impactful issues first.
Example:
A financial institution experiences an increase in transaction errors leading to customer complaints. Process mining analysis highlights discrepancies in data entry processes as a prevalent issue. Conducting Pareto Analysis based on process mining data reveals that 80% of errors stem from 20% of data entry fields. By focusing efforts on improving the accuracy of these high-impact fields, the institution can achieve a significant reduction in transaction errors.
This is probably the best example as you NEED to do this to process the amount of data provided by process mining. When looking at a process mining visualization, it is imperative to filter out the noise and focus on the most common error types. Combining this technique with others to ensure you are correctly selecting cases will set you up to address the issue’s root cause.
Integrating Lean Six Sigma techniques and tools with process mining outputs enhances the depth and effectiveness of root cause analysis efforts. The whole point of process efficient efforts is to lean out processes, improve outputs and generate a positive ROI. Leveraging technology to rapidly provide process insights and then follow up by bringing the process stakeholders through six sigma workshops results in the most favorable way to generate a positive outcome. Embracing this synergistic approach empowers organizations to achieve higher levels of operational excellence and combine the best of both old or new techniques.