High-Level Event Mining: A Framework

Process mining can be viewed as the missing link between model-based process analysis and data-oriented analysis techniques. Lion's share of process mining research has been focusing on process discovery (creating process models from raw data) and replay techniques to check conformance and analyze bottlenecks. These techniques have helped organizations to address compliance and performance problems. However, for a more refined analysis, it is essential to correlate different process characteristics. For example, do deviations from the normative process cause additional delays and costs? Are rejected cases handled differently in the initial phases of the process? What is the influence of a doctor's experience on treatment process? These and other questions may involve process characteristics related to different perspectives (control-flow, data-flow, time, organization, cost, compliance, etc.). Specific questions (e.g., predicting the remaining processing time) have been investigated before, but a generic approach was missing thus far. The proposed framework unifies a number of approaches for correlation analysis proposed in literature, proposing a general solution that can perform those analyses and many more. The approach has been implemented in ProM and combines process and data mining techniques. In this paper, we also demonstrate the applicability using a case study conducted with the UWV (Employee Insurance Agency), one of the largest "administrative factories" in The Netherlands.

Atas da 17ª Conferência da Associação Portuguesa de Sistemas de Informação, 2017

Business Process Management (BPM) is a well-known discipline, with roots in previous theories related with optimizing management and improving businesses results. One can trace BPM back to the beginning of this century, although it was in more recent years when it gained a special focus of attention. Usually, traditional BPM approaches start from top and analyse the organization according some known rules from its structure or from the type of business. Process Mining (PM) is a completely different approach, since it aims to extract knowledge from event logs, which are widely present in many of today's organizations. PM uses specialized data-mining algorithms, trying to uncover patterns and trends in these logs, and it is an alternative approach where formal process specification is not easily obtainable or is not cost-effective. This paper makes a literature review of major works issued about this theme.

Application and Theory of Petri Nets and Concurrency, 2015

Process mining is a family of methods to analyze event logs produced during the execution of business processes in order to extract insights regarding their performance and conformance with respect to normative or expected behavior. The landscape of process mining methods and use cases has expanded considerably in the past decade. However, the field has evolved in a rather ad hoc manner without a unifying foundational theory that would allow algorithms and theoretical results developed for one process mining problem to be reused when addressing other related problems. In this paper we advocate a foundational approach to process mining based on a well-known model of concurrency, namely event structures. We outline how event structures can serve as a unified representation of behavior captured in process models and behavior captured in event logs. We then sketch how process mining operations, specifically automated process discovery, conformance checking and deviance mining, can be recast as operations on event structures.

This demo introduces Eventifier, a tool that helps in reconstructing an event log from operational databases upon which process instances have been executed. The purpose of reconstructing such event log is that of discovering process models out of it, and, hence, the tool targets researches and practitioners interested in process mining. The aim of this demo is to convey to the participants both the conceptual and practical implications of identifying and extracting process execution events from such databases for reconstructing ready-to-use event logs for process discovery.

Process discovery algorithms aim to capture process orchestration models from event logs. These algorithms have been designed for logs in which events that belong to the same case are related to each other-and to that case-by means of a unique case identifier. However, in service oriented systems these case identifiers are usually not stored beyond request-response pairs, which makes it hard to relate events that belong to the same case. This is known as the correlation challenge. This paper addresses the correlation challenge by introducing a new process discovery algorithm, called the correlation miner, that facilitates process discovery when events are not associated with a case identifier. Experiments performed on both synthetic and real-world event logs show the applicability of the correlation miner.

Process mining techniques use event data to answer a variety of process-related questions. Process discovery, conformance checking, model enhancement, and operational support are used to improve performance and compliance. Process mining starts from recorded events that are each characterized by a case identifier, an activity name, a timestamp, and optional attributes like resource or costs. In many applications, there are multiple candidate identifiers leading to different views on the same process. Moreover, one event may be related to different cases (convergence) and, for a given case, there may be multiple instances of the same activity within a case (divergence). To create a traditional process model, the event data need to be "flattened". There are typically multiple choices possible, leading to different views that are disconnected. Therefore, one quickly loses the overview and event data need to be exacted multiple times (for the different views). Different approaches have been proposed to tackle the problem. This paper discusses the gap between real event data and the event logs required by traditional process mining techniques. The main purpose is to create awareness and to provide ways to characterize event data. A specific logging format is proposed where events can be related to objects of different types. Moreover, basic notations and a baseline discovery approach are presented to facilitate discussion and understanding.

arXiv (Cornell University), 2023

Process mining techniques aim to analyze and improve conformance and performance of processes using event data. Process discovery is the most prominent process-mining task: A process model is derived based on an event log. The process model should be able to capture causalities, choices, concurrency, and loops. Process discovery is very challenging because of trade-offs between fitness, simplicity, precision, and generalization. Note that event logs typically only hold example behavior and cannot be assumed to be complete (to avoid overfitting). Dozens of process discovery techniques have been proposed. These use a wide range of approaches, e.g., language-or state-based regions, genetic mining, heuristics, expectation maximization, iterative log-splitting, etc. When models or logs become too large for analysis, the event log may be automatically decomposed or traces may be clustered before discovery. Clustering and decomposition are done automatically, i.e., no additional information is used. This paper proposes a different approach where a localized event log is assumed. Events are localized by assigning a non-empty set of regions to each event. It is assumed that regions can only interact through shared events. Consider for example the mining of software systems. The events recorded typically explicitly refer to parts of the system (components, services, etc.). Currently, such information is ignored during discovery. However, references to system parts may be used to localize events. Also in other application domains, it is possible to localize events, e.g., communication events in an organization may refer to multiple departments (that may be seen as regions). This paper proposes a generic process discovery approach based on localized event logs. The approach has been implemented in ProM and experimental results show that location information indeed helps to improve the quality of the discovered models.

Lecture Notes in Electrical Engineering, 2016

Process mining is a set of techniques helping enterprises to avoid process modeling which is time consuming and error prone tasks. The goal of such techniques is to extract the process as it has been executed. However, the increase of data production in event logs of process aware information systems makes it necessary to mine the processes in real time. For this purpose, it is necessary to define new approaches for process discovery analyzing data on the fly. This paper presents a new process discovery approach aiming to extract data on the fly by discovering the set of blocks composing the process.

Lecture Notes in Computer Science, 2009

Process mining refers to the extraction of process models from event logs. Real-life processes tend to be less structured and more flexible. Traditional process mining algorithms have problems dealing with such unstructured processes and generate spaghetti-like process models that are hard to comprehend. One reason for such a result can be attributed to constructing process models from raw traces without due pre-processing. In an event log, there can be instances where the system is subjected to similar execution patterns/behavior. Discovery of common patterns of invocation of activities in traces (beyond the immediate succession relation) can help in improving the discovery of process models and can assist in defining the conceptual relationship between the tasks/activities. In this paper, we characterize and explore the manifestation of commonly used process model constructs in the event log and adopt pattern definitions that capture these manifestations, and propose a means to form abstractions over these patterns. We also propose an iterative method of transformation of traces which can be applied as a pre-processing step for most of today's process mining techniques. The proposed approaches are shown to identify promising patterns and conceptually-valid abstractions on a real-life log. The patterns discussed in this paper have multiple applications such as trace clustering, fault diagnosis/anomaly detection besides being an enabler for hierarchical process discovery.