Technology Blog: Process mining

Process mining is a family of techniques in the field of process management that support the analysis of business processes based on event logs. During process mining, specialized data mining algorithms are applied to event log data in order to identify trends, patterns and details contained in event logs recorded by an information system. Process mining aims to improve process efficiency and understanding of processes.[1] Process mining is also known as Automated Business Process Discovery (ABPD). However, in academic literature[3] the term Automated Business Process Discovery is used in a narrower sense to refer specifically to techniques that take as input an event log and produce as output a business process model. The term Process Mining is used in a broader setting to refer not only to techniques for discovering process models, but also techniques for business process conformance and performance analysis based on event logs.

Application
Process mining follows the options established in business process engineering, then goes beyond those options by providing feedback for business process modeling:

process analysis filters, orders and compresses logfiles for further insight into the connex[further explanation needed] of process operations.
process design may be supported by feedback from process monitoring (action or event recording or logging)
process enactment uses results from process mining based on logging for triggering further process operations

Classification
There are three classes of process mining techniques. This classification is based on whether there is a prior model and, if so, how the prior model is used during process mining.

Discovery: Previous (a priori) models do not exist. Based on an event log, a new model is constructed or discovered based on low-level events. For example, using the alpha algorithm (a didactically driven approach).Many established techniques exist for automatically constructing process models (for example, Petri net, pi-calculus[9][better source needed] expression) based on an event log.Recently, process mining research has started targeting the other perspectives (e.g., data, resources, time, etc.). One example is the technique described in (Aalst, Reijers, & Song, 2005),which can be used to construct a social network.
Conformance checking: Used when there is an a priori model. The existing model is compared with the process event log; discrepancies between the log and the model are analyzed. For example, there may be a process model indicating that purchase orders of more than 1 million Euro require two checks. Another example is the checking of the so-called "four-eyes" principle. Conformance checking may be used to detect deviations to enrich the model. An example is the extension of a process model with performance data, i.e., some a priori process model is used to project the potential bottlenecks. Another example is the decision miner described in (Rozinat & Aalst, 2006b) which takes an a priori process model and analyzes every choice in the process model. For each choice the event log is consulted to see which information is typically available the moment the choice is made. Then classical data mining techniques are used to see which data elements influence the choice. As a result, a decision tree is generated for each choice in the process.
Performance Mining: Used when there is an a priori model. The model is extended with a new performance information such as processing times, cycle times, waiting times, costs, etc., so that the goal is not to check conformance, but rather to improve the performance of the existing model with respect to certain process performance measures. An example is the extension of a process model with performance data, i.e., some prior process model dynamically annotated with performance data.