Conformance Checking: Foundations, Milestones and Challenges

Process mining enables organizations to uncover their actual processes, provide insights, diagnose problems, and automatically trigger corrective actions. Process mining is an emerging scientific discipline positioned at the intersection between process science and data science. The combination of process modeling and analysis with the event data present in today’s information systems provides new means to tackle compliance and performance problems. This chapter provides an overview of the field of process mining introducing the different types of process mining (e.g., process discovery and conformance checking) and the basic ingredients, i.e., process models and event data. To prepare for later chapters, event logs are introduced in detail (including pointers to standards for event data such as XES and OCEL). Moreover, a brief overview of process mining applications and software is given.

“…Several conformance checking techniques are explained in detail in [15]. When comparing observed and modeled behavior, we typically consider four main quality dimensions [1,2,6]:…”

Section: Conformance Checkingmentioning

confidence: 99%

Process Mining: A 360 Degree Overview

Aalst

2022

“…In some cases, the process behavior is too complex to be captured by a single case notion and multi dimensional or multi entity representation are required to avoid drawing inaccurate conclusions [19]. Conformance checking techniques such as alignments [20] often face the challenge that there are multiple possible explanations for a non-conformance between observed and prescribed process behavior. However, it may be infeasible to show all of them due to the large number of possibilities.…”

Section: Process Mining Perspectivementioning

confidence: 99%

“…Classically, process mining quality dimensions consist of fitness, precision, generalization, and simplicity as introduced in [1]. For most of these quality dimensions measures have been proposed that are based on conformance checking, e.g., through alignments as indicated in [20]. However, this common practice of measuring model quality has been challenged at least for precision with Tax et al [29] proposing several axioms that the prevalent measures do not fulfil.…”

Section: Model Qualitymentioning

confidence: 99%

Responsible Process Mining

Mannhardt

2022

The prospect of data misuse negatively affecting our life has lead to the concept of responsible data science. It advocates for responsibility to be built, by design, into data management, data analysis, and algorithmic decision making techniques such that it is made difficult or even impossible to intentionally or unintentionally cause harm. Process mining techniques are no exception to this and may be misused and lead to harm. Decisions based on process mining may lead to unfair decisions causing harm to people by amplifying the biases encoded in the data by disregarding infrequently observed or minority cases. Insights obtained may lead to inaccurate conclusions due to failing to considering the quality of the input event data. Confidential or personal information on process stakeholders may be leaked as the precise work behavior of an employee can be revealed. Process mining models are usually white-box but may still be difficult to interpret correctly without expert knowledge hampering the transparency of the analysis. This chapter structures the topic of responsible process mining based on the FACT criteria: Fairness, Accuracy, Confidentiality, and Transparency. For each criteria challenges specific to process mining are provided and the current state of the art is briefly summarized.

“…This technique can be seamlessly lifted to handle the standard conformance checking task, where conformance is evaluated on an event log containing full traces of already completed process executions (cf. [16]). In this setting, the global automaton is not needed anymore, as a-posteriori it is not relevant to compute the earliest moment of a violation, but only to properly detect it at the trace level.…”

Section: A Note On Conformance Checkingmentioning

confidence: 99%

“…Finer-grained feedbacks like those based on the computation of trace alignments have been extensively applied for procedural models (cf. [16]), and can be also of the Declare specification of interest. This is an active line of research, which started from the seminal approach in [31].…”

Section: A Note On Conformance Checkingmentioning

confidence: 99%

Declarative Process Specifications: Reasoning, Discovery, Monitoring

Aalst

Montali

2022

The declarative specification of business processes is based upon the elicitation of behavioural rules that constrain the legal executions of the process. The carry-out of the process is up to the actors, who can vary the execution dynamics as long as they do not violate the constraints imposed by the declarative model. The constraints specify the conditions that require, permit or forbid the execution of activities, possibly depending on the occurrence (or absence) of other ones. In this chapter, we review the main techniques for process mining using declarative process specifications, which we call declarative process mining. In particular, we focus on three fundamental tasks of (1) reasoning on declarative process specifications, which is in turn instrumental to their (2) discovery from event logs and their (3) monitoring against running process executions to promptly detect violations. We ground our review on Declare, one of the most widely studied declarative process specification languages. Thanks to the fact that Declare can be formalized using temporal logics over finite traces, we exploit the automata-theoretic characterization of such logics as the core, unified algorithmic basis to tackle reasoning, discovery, and monitoring. We conclude the chapter with a discussion on recent advancements in declarative process mining, considering in particular multi-perspective extensions of the original approach.