In process mining, we use algorithms to analyze event data and reveal details about the activities performed by people and machines.

Process mining has a wide range of applications across various disciplines including finance, healthcare, manufacturing and logistics. It’s an interdisciplinary field that combines techniques from data mining, machine learning and process management to discover, monitor and optimize real-world business processes. With process mining, organizations can increase efficiency and ensure widespread compliance.

3 Types of Process Mining

  1. Discovery
  2. Conformance
  3. Enhancement

More From This ExpertWhat Is Software Quality Assurance?

 

How Does Process Mining Work?

In a typical process mining scenario, we collect data from various sources such as an organization’s transaction logs, ticketing systems, ordering systems, and CRM (customer relationship management) and ERP (enterprise resource planning) systems in the form of event logs.

You can see a simple event log from a hospital below. To properly develop the process model, event logs should contain case ID, activity and timestamp information at the minimum.

process mining chart as described by author
A simple medical event log. | Image: Erdem Isbilen

Here, case ID represents a specific instance of the process from start to finish. A case ID can have many activities with different timestamps. In the table above, case ID of 1000 covers a specific service provided to a patient, which contains three different activities.

Timestamps provide critical records of when the activities occurred and in what order. Process mining algorithms use this information to generate process flows, measure performance and monitor compliance. 

Process mining algorithms scan the event logs to provide insight into the structure of the underlying process. We then process the outcome of the analysis using specialized software tools that can visualize the process flow, identify inefficiencies and detect patterns.

Process mining map; Relevant details described by author below.
A graphical representation of a simple process model derived by process mining for a hospital. Process maps provide a visual representation of the processes along with a wealth of statistical information. | Image: Erdem Isbilen

 

Frequency Counts

The process map above displays the daily frequency of activities. In a single day, examination room one handled 134 patients and examination room two covered 74 patients.

 

Cycle Times

The process map uses timestamps to display the cycle times for a particular task from start to finish while also providing information about the average cycle times over weeks and months.

 

Resource Utilization

When management analyzes the process map above, they can see 194 patients (83 percent of registered patients) received blood tests while only 32 X-ray tests were conducted on this day. This data helps management allocate resources based on the demand for different tests.

 

Process Variants and Deviations

Process maps can show process variants including deviations from the expected process flow. This helps identify areas of the process that need to be standardized or optimized. In the process map above, you can see that although 234 patients are registered, 215 of them are discharged by the hospital. That means 19 patients left the hospital without being examined and discharged. Once we investigate, we may find that patients are leaving the hospital without being seen due to the long wait times. 

What Is Process Mining? | Video: IBM Technology

 

Types of Process Mining

1. Discovery

In some cases, an organization may not have a proper process model definition. In such cases, we would use process mining to develop a process model.

Alpha-algorithm, heuristic-mining algorithm and genetic-process-mining algorithm are among the algorithms we use to extract process models from the event logs. Process discovery algorithms scan through all the events in the log to develop the process model.

We can then develop graphical representations of the process models using industry-standard notations such as directly-follows graphs, petri-nets, and BPMN 2.0 (Business Process Model and Notation).

 

2. Conformance

Organizations often have an ideal process model in place that defines how a process is supposed to work. In conformance process mining, the actual execution of a process is compared with a predefined process model. Conformance-type process mining aims to identify deviations that may include redundant or unnecessary steps, as well as missed or incorrectly sequenced steps.

This information can help organizations identify inefficiencies, non-compliance with regulations or standards and other areas for improvement. 

 

3. Enhancement

Once we develop the process model and identify the areas for improvement, process mining enhancement involves redesigning the process to optimize its efficiency and effectiveness. This process includes eliminating unnecessary steps, automating repetitive tasks and reallocating resources, all while improving team communication and collaboration.

 

Benefits of Process Mining

Process Flow, Variations and Exceptions

The process model clearly shows the process steps and their sequences as well as process variations and exceptions (if there are any). With this information, you can identify inefficiencies, bottlenecks and opportunities for operational improvement.

 

Process Performance Metrics and Resource Utilization

Process mining helps you see the process performance metrics and resource utilization more clearly. This means you can get a better idea of how organizations use resources including people, machines and materials. This information helps organizations optimize resource allocation and improve overall efficiency.

 

Compliance and Regulatory Requirements

Process models demonstrate deviations from compliance and regulatory requirements. Organizations use this information to ensure that the process is aligned with legal and regulatory standards.

More From Our Ops and Efficiency ExpertsWhat Is Lean Six Sigma?

 

Tools for Process Mining 

Celonis

Celonis offers execution management solutions to help organizations optimize their business processes. They provide a suite of process mining capabilities that allow companies to gain better visibility into their operations, identify areas of inefficiency and streamline their workflows. These capabilities leverage machine learning, industry-standard process query language (PQL) and include features such as: 

  • Customizable analytic visualizations
  • Task mining
  • Flexible data models
  • Support for multiple event logs
  • Benchmarking against industry best practices 
  • Identification of processes ripe for automation 
Process Mining Explained. | Video: Celonis

 

Fluxicon Disco

Fluxicon is a provider of process mining solutions designed for business process managers and consultants. The company’s flagship product, Disco, offers a range of advanced features, including process map animations, detailed statistics, interactive charts, automated process discovery and user-friendly log filters that allow users to drill deeper into their data. Additionally, Disco provides project management capabilities and performance filters while supporting various data import and export options.

 

IBM Process Mining 

IBM’s suite of process mining products leverages data-driven insights to enable companies across various industries to enhance their processes and make informed decisions quickly. IBM’s process mining solutions have numerous use cases, such as intelligent automation, customer onboarding, P2P (procure to pay), accounts payable, IT incident management and order-to-cash. 

IBM’s process mining tools offer features such as automated RPA (robotic process automation) generation, fact-based process models, AI-driven process simulations, conformance checking, task mining and seamless integrations with leading software providers like SAP, Oracle and other IBM products. 

 

Process Mining vs. Data Mining

Process mining and data mining are both fields that involve the analysis of large data sets, but they have distinct differences. 

  • Process mining focuses on analyzing and improving business processes while data mining focuses on discovering patterns and insights in data sets more generally.
  • Process mining mainly uses event logs or transaction data generated by business processes, whereas data mining uses a variety of data sources, including social media, customer and financial data.
  • Process mining techniques are specifically designed to analyze the behavior of business processes, such as process discovery, conformance checking and performance analysis. Data mining techniques, on the other hand, are more general and can include clustering, classification and regression.

Process mining objectives are primarily aimed at improving the efficiency and effectiveness of business processes. In contrast, data mining can have a wider range of goals, such as identifying new marketing opportunities, detecting fraudulent activities or predicting customer behavior.

Expert Contributors

Built In’s expert contributor network publishes thoughtful, solutions-oriented stories written by innovative tech professionals. It is the tech industry’s definitive destination for sharing compelling, first-person accounts of problem-solving on the road to innovation.

Learn More

Great Companies Need Great People. That's Where We Come In.

Recruit With Us