FI-DPA 12 Projekt — Process-Discovery-Fallstudie (EN)

FI-DPA 12 Project — Process-Discovery Case Study

In this module, you will conduct a complete Process-Discovery analysis—from preparing log data to applying Process-Mining techniques and creating a KPI dashboard to deriving improvement measures. You will learn how to systematically analyze real process data to identify inefficiencies, bottlenecks, and compliance deviations in business processes.

The case study is based on a fictional e-commerce scenario where you analyze the order process from customer inquiry to delivery. You will apply various Process-Mining algorithms, visualize the processes, and derive data-driven optimization measures.

Concepts and Background

Event Log

Chronological recording of events in a process that serves as the basis for Process-Mining analyses. Each entry typically contains case ID, activity, timestamp, and additional attributes.

Process Mining

Analytical technique that reconstructs actual process flows from event data and compares them with the as-is state. Three main approaches are Discovery, Conformance Checking, and Enhancement.

KPI Dashboard

Visualization of process key performance indicators for monitoring and controlling business processes. Contains metrics such as lead time, costs, quality indicators, and efficiency measures.

Process Discovery

Investigation of event data to identify and visualize unknown or implicit process models without making predefined assumptions about the process flow.

Conformance Checking

Procedure to verify whether actual process behavior corresponds to a reference model (e.g., from BPMN). Identifies deviations and inefficiencies.

Architecture Diagram

flowchart TD
    A[Log Sources] --> B[ETL Process]
    B --> C[Process-Mining Tool]
    C --> D[Process Visualization]
    D --> E[KPI Calculation]
    E --> F[Dashboard]
    F --> G[Optimization Measures]
    G --> H[Process Implementation]

Practical Steps

1. Collect and prepare log data. Extract relevant event data from various system sources such as CRM, ERP, and Warehouse Management.
2. Convert Event Log to XES format. Use the Open-XES toolkit to standardize the event data structure.
3. Perform Process-Mining analysis with the Alpha algorithm. Identify basic process models and their characteristic patterns.
4. Perform heuristic process analysis. Apply the HeuristicsMiner to recognize complex dependencies between activities.
5. Define and calculate KPIs. Determine metrics such as lead time, cycle time, and resource utilization for different process paths.
6. Create process visualization. Generate Petri nets or BPMN models from the analyzed data to clarify the process flows.
7. Perform Conformance Checking. Compare actual process behavior with the target model and document deviations.
8. Implement KPI dashboard. Create interactive visualizations with tools like Power BI or Tableau to monitor process performance.
9. Identify optimization potential. Analyze bottlenecks, waiting times, and unnecessary activities to derive improvement measures.
10. Implement and monitor improvement measures. Introduce the identified optimizations into the process and monitor their effect.

Common Pitfalls

Further Resources

• Process Mining Manifesto - Official resource of the Process-Mining community
• Fluxion Process Mining Tutorials - Extensive learning materials and case studies
• Process Mining Excellence Center - Research results and best practices
• Process Mining YouTube Channel - Video tutorials and webinars
• Process Mining: Data Science in Action - Standard work by Wil van der Aalst

Knowledge Check

Four questions for self-assessment. Click on each question to see the correct answer and explanation.

What is the primary goal of Process-Discovery analysis?

• A) Checking whether actual processes match target models
• B) Identification of unknown or implicit process models from event data
• C) Calculation of process key performance indicators for monitoring
• D) Automation of business processes

Correct Answer: B. Process-Discovery aims to identify unknown process models from event data without making predefined assumptions. Option A describes Conformance Checking, option C KPI dashboards, and option D is process automation.

Which format is typically used for Event Logs in Process-Mining analyses?

• A) XML
• B) CSV
• C) XES
• D) JSON

Correct Answer: C. XES (eXtensible Event Stream) is the standard format for Event Logs in Process-Mining. While CSV and JSON can also be used, XES was specifically developed for Process-Mining analyses. XML is related but not the primary format.

What is the main difference between Process Discovery and Conformance Checking?

• A) Process Discovery uses KPI dashboards, Conformance Checking does not
• B) Process Discovery identifies unknown processes, Conformance Checking checks compliance with target models
• C) Process Discovery requires Event Logs, Conformance Checking does not
• D) Process Discovery is for real data, Conformance Checking only for simulated data

Correct Answer: B. Process Discovery identifies unknown p