A genetic programming approach to business process mining

Process mining (PM) is a technique to extract a process model from an event log to represent the process behaviour recorded in that event log. A mined process model with high fitness means that it can reflect most of the process behaviour recorded in the event log. Previous studies have shown that the mined model with high fitness can be used in process improvement, such as fraud detection, continuous process improvement and benchmarking. Genetic process mining (GPM) is a famous PM approach, which can simultaneously identify several process structures from event logs. However, GPM cannot effectively discover parallel structures from event logs. This study proposes a PM approach based on integration of GPM, particle swarm optimisation and differential evolution to find process models with high fitness for event logs involving multiple parallel structures. The results show that the proposed approach does indeed lead to improvement in gaining process models with high fitness for event logs involving multiple parallel structures.

The current business environment has no room for inefficiency as it can cause companies to lose out to their competitors, to lose customer trust, and to experience cost overruns. Business processes within the company continue to grow and cause them to run more complex. The large scale and complexity of business processes pose a challenge in improving the quality of process model because the effectiveness of time and the efficiency of existing resources are the biggest challenges. In the context of optimizing business processes with a process mining approach, most current process models are optimized with a trace clustering approach to explore the model and to perform analysis on the resulting process model. Meanwhile, in the event log data, not only the activities but also the other resources, such as records of employee or staff working time, process service time, and processing costs, are recorded. This article proposes a mechanism alternative to optimize business processes by exploring the resources that occur in the process. The mechanism is carried out in three stages. The first stage is optimizing the job shop scheduling method from the generated event log. Scheduling the time becomes a problem in the job shop. Utilizing the right time can increase the effectiveness of performance in order to reduce costs. Scheduling can be defined as the allocation of multiple jobs in a series of machines, in which each machine only does one job at a time. In general, scheduling becomes a problem when sequencing the operations and allocating them into specific time slots without prolonging the technical and capacity constraints. The second stage is generating the resource value that is recorded in the event log from the results of analysis of the previous stage, namely, job shop scheduling. The resource values are multivariate and then clustered to determine homogeneous clusters. The last stage is optimizing the nonlinear multipolynomials in the homogeneous cluster formed by using the Hessian solution. The results obtained are analyzed to get recommendations on business processes that are appropriate for the company’s needs. The impact of long waiting times will increase service costs, but by improving workload, costs can be reduced. The process model and the value of service costs resulting from the mechanism in the research can be a reference for process owners in evaluating and improving ongoing processes.

The topic of process mining has attracted the attention of both researchers and tool vendors in the Business Process Management (BPM) space. The goal of process mining is to discover process models from event logs, i.e., events logged by some information system are used to extract information about activities and their causal relations. Several algorithms have been proposed for process mining. Many of these algorithms cannot deal with concurrency. Other typical problems are the presence of duplicate activities, hidden activities, non-free-choice constructs, etc. In addition, real-life logs contain noise (e.g., exceptions or incorrectly logged events) and are typically incomplete (i.e., the event logs contain only a fragment of all possible behaviors). To tackle these problems we propose a completely new approach based on genetic algorithms. As can be expected, a genetic approach is able to deal with noise and incompleteness. However, it is not easy to represent processes properly in a genetic setting. In this paper, we show a genetic process mining approach using the so-called causal matrix as a representation for individuals. We elaborate on the relation between Petri nets and this representation and show that genetic algorithms can be used to discover Petri net models from event logs.KeywordsProcess MiningPetri NetsGenetic AlgorithmsProcess DiscoveryBusiness Process IntelligenceBusiness Activity Monitoring

Process Mining helps to analyze and interpret business processes using event logs of information systems as ground truth. It has been successfully applied to process-oriented enterprise systems but is less suited for communication- and document-oriented Enterprise Collaboration Systems (ECS). This is due to two core characteristics of ECS processes and process logging. On the one hand, ECS processes are highly unstructured as their usage is not related to predefined business processes. The usage of ECS is ad-hoc and flexible. On the other hand, ECS commonly provide rather low-level process logs, i. e., logged events are very fine-granular, and, thus hard to interpret. Both characteristics lead to so-called spaghetti process models, which are barely interpretable when applying “traditional” process mining to ECS. This work focuses on the second aspect, i. e., to solve the problem of too fine-granular process logs of ECS. A common solution and preprocessing step for this granularity challenge is event abstraction, i.e., converting low-level logs into more abstract high-level logs before applying further process mining analysis techniques. ECS logs come with special characteristics that have so far not been fully addressed by existing event abstraction approaches. We aim to close this gap with a tailored ECS event abstraction (ECSEA) approach that trains a model by comparing observed actual user activities (also named high-level traces) with the system-generated low-level traces. The model allows us to automatically convert historic and future low-level traces into abstracted high-level traces that can be used for Process Mining. This article describes the ECS event log characteristics, introduces the proposed ECSEA approach with the underlying algorithms, and shows a corresponding evaluation. Our two-fold evaluation shows that the algorithm produces accurate results. In the evaluation, we use both synthetic and real-world event data taken from a productive ECS with more than 4000 users currently running at a university. • Derivation of relevant low-level event log characteristics: Based on a comparison of low-level and related high-level event logs, we derive low-level event log characteristics. They serve as requirements for a novel event abstraction approach and are further used for a comparison of related approaches. • Conceptualization of a novel supervised event abstraction approach: The main contribution is a novel event abstraction algorithm, which is described and evaluated in this article.

Many present-day companies carry out a huge amount of daily operations through the use of their information systems without ever having done their own enterprise modeling. Business process mining is a well-proven solution which is used to discover the underlying business process models that are supported by existing information systems. Business process discovery techniques employ event logs as input, which are recorded by process-aware information systems. However, a wide variety of traditional information systems do not have any in-built mechanisms with which to collect events (representing the execution of business activities). Various mechanisms with which to collect events from non-process-aware information systems have been proposed in order to enable the application of process mining techniques to traditional information systems. Unfortunately, since business processes supported by traditional information systems are implicitly defined, correlating events into the appropriate process instance is not trivial. This challenge is known as the event correlation problem. This paper presents an adaptation of an existing event correlation algorithm and incorporates it into a technique in order to collect event logs from the execution of traditional information systems. The technique first instruments the source code to collect events together with some candidate correlation attributes. Based on several well-known design patterns, the technique provides a set of guidelines to support experts when instrumenting the source code. The event correlation algorithm is subsequently applied to the data set of events to discover the best correlation conditions, which are then used to create event logs. The technique has been semi-automated to facilitate its validation through an industrial case study involving a writer management system and a healthcare evaluation system. The study demonstrates that the technique is able to discover an appropriate correlation set and obtain well-formed event logs, thus enabling business process mining techniques to be applied to traditional information systems.

Since IoT devices supporting business processes (BPs) in sectors like manufacturing, logistics or healthcare can collect data on the execution of the processes, there is a growing awareness of the opportunity to use IoT data for process mining (PM). However, several challenges need to be addressed to enable IoT-enhanced PM, among which the need for a standard IoT-enhanced event log model. In this paper, we identify four main challenges for the integration of IoT data in event logs, from which 10 requirements for an IoT-enhanced event log model are derived. We then analyse the two main current event log models, the extensible event stream (XES) and the object-centric event log (OCEL), and confront them with the requirements, showing that both present important limitations to storing IoT-enhanced event logs. Based on this analysis, we conclude that a comprehensive data model is required to develop more advanced IoT-enhanced PM techniques .KeywordsProcess miningIoTIoT-enhanced event log

Combination of Process Mining and Causal Discovery Generated Graph Models for Comprehensive Process Modeling

Business process management (BPM) is a well-established discipline comprising a set of principles, methods, techniques, and tools to continuously improve the performance of business processes. Traditionally, most BPM decisions and activities are undertaken by business stakeholders based on manual data collection and analysis techniques. This is time-consuming and potentially leads to suboptimal decisions, as only a restricted subset of data and options are considered. Over the past decades, a rich set of data-driven techniques has emerged to support and automate various activities and decisions across the BPM lifecycle, particularly within the process mining field. More recently, the uptake of artificial intelligence (AI) methods for BPM has led to a range of approaches for proactive business process monitoring. Given their common data requirements and overlapping goals, process mining and AI-driven approaches to business process optimization are converging. This convergence is leading to a promising emerging concept, which we call (AI-)augmented process execution: a collection of data analytics and artificial intelligence methods for continuous and automated improvement and adaptation of business processes. This article gives an outline of research at the intersection between process mining and AI-driven process optimization, classifies the researched techniques based on their scope and objectives, and positions augmented process execution as an additional layer on top of this stack.

Process Mining analyzes event logs from business processes to enhance understanding, verification, and improvement of these processes. Event logs typically originate from multiple sources and require extensive preprocessing before applying process mining techniques. This preprocessing includes filtering, composing, joining events into traces, and fixing or calculating attribute values. Existing process mining tools offer ad-hoc manual actions through graphical interfaces and simple domain-specific languages, but these methods have limitations, and there is no standardized approach for processing event logs. The primary contribution of this work is the Process Query Language (PQL), a domain-specific language (DSL) for processing event logs that surpasses current techniques. We begin by analyzing several existing DSLs concerning key success factors, followed by an evaluation of current business process DSLs to identify their limitations. Based on this analysis, we propose the PQL specification as a draft technical standard. PQL’s design decisions are validated through an interpreter implementation and its application to numerous use cases.

Towards interactive event log forensics: Detecting and quantifying timestamp imperfections

Process mining analyzes business processes using event logs. Existing tools generate models to facilitate this task and improve the original business process, but the results are often unsatisfactory due to the complexity of the obtained models. Among the challenges faced in this context, we identify the misalignment with specific business requirements, preventing managers from accessing key data and making effective decisions. In this paper, we propose a requirement-driven approach centered on meta-modeling, which can help the development of process mining tools specially tailored to organizational needs. Thus, we introduce a requirement-driven method to address the critical challenge of model misalignment with required information. The method employs Model-Driven Engineering to simplify how process mining results are formulated, analyzed, and interpreted. The proposed method is iterative and involves several steps. First, a service manager defines a specific business question. Second, service managers and developers collaboratively establish a meta-model representing the target data. Third, developers extract relevant data using appropriate analysis techniques and visualize it. Finally, service managers and developers jointly interpret these visualizations to inform strategic decisions. This requirement-driven methodology empowers developers to concentrate on relevant information. Unlike general-purpose frameworks (e.g., ProM, Disco), this method emphasizes specificity, iterative refinement, and close stakeholder collaboration. By reducing cognitive overload through focused modeling and filtering of irrelevant data, organizations adopting this approach can achieve faster response times to business questions and develop specialized in-house analytical tools. This requirement-driven methodology, therefore, improves decision-making capabilities within process mining and across related analytical domains. We illustrate our methodology through a real business process taken from the literature owned by the VOLVO group. We use several examples of process mining to illustrate the benefits of the proposed methodology compared to existing tools which are unable to provide the required information. • A requirement-driven meta-model method for standardized process-mining assessment. • An iterative approach for low-cost development of tailored in-house tools. • Improves decisions through focused data extraction and need-aligned analysis.

Process mining is an emerging discipline incorporating methods and tools for the analysis of system/process executions captured in the form of event logs [1]. Traditionally process mining can be divided into three research areas: discovery (construction of process models from event logs), conformance checking (finding log and model deviations), and enhancement of existing process models with additional event log data.BPMN (Business Process Model and Notation) 2.0 [2] is a widely used process modeling notation, supported by various process modeling and analysis tools, and is a de-facto process modeling standard. Using BPMN within process mining opens perspectives for applicability of the existing process mining techniques: for instance discovered process models can be analyzed or enacted using existing BPMN-based software, and vice versa, manually created models can be imported to a process mining tool, verified against event logs, and enhanced with additional data.In this work we bridge the gap between conventional process modeling formalisms used in the context of process mining (e.g., Petri nets, causal nets, process trees) and BPMN. For that purpose we developed a suite of conversion algorithms and provide formal guarantees relating the behavior of Petri nets (including non-free-choice nets) to the corresponding BPMN models (and vice versa). The derived relations are used to enhance the BPMN models with information learned from the event logs.The developed conversion techniques are described in detail in [3] and have been implemented [4] as a part of ProM (Process Mining Framework) [5] -- an open source tool for process mining and verified on real event log data. Moreover, cases for which conversion algorithms give more compact process models in comparison with the initial models are identified. Although the developed algorithms deal with basic control flow constructs only, they can be applied in the discovery of advanced BPMN modeling elements [2], including subprocesses [6-7], cancellations [8], conditional branching and data objects, swimlanes, message flows, and others.

Process mining empowers companies to optimise operational processes by deriving insights from event logs. It involves assessing event logs or the resultant process models against existing models and identifying challenges within executed processes to enhance their efficiency. However, a critical prerequisite for effective process mining is data cleaning, which simplifies the complexities inherent in real-world event data, making it amenable to comprehension, processing, and leveraging with process mining techniques. Consequently, new methodologies and approaches for event data pre-processing have garnered significant attention within the business process scientific community. This paper presents a systematic literature review summarising relevant techniques for event data pre-processing in the context of business process mining. The objective of this study is to categorise approaches and methodologies related to event data pre-processing while shedding light on the crucial issues associated with these techniques.

The performance of business processes is a critical success factor for companies on highly competitive markets. The improvement of business processes requires a deep understanding of as-is processes and existing weaknesses that hamper their performance. Traditionally, process mapping and weakness detection are conducted manually based on workshops and interviews with employees involved in the process. Consequently, these practices are not merely time-consuming and costly, but at the same time liable to subjective influences of the interviewed participants. For process mapping, these challenges can be overcome with the data based technology of process mining, that can model as-is-processes based on event log data from companies' information systems. For weakness detection in business processes, however, this technology is not applicable yet since this step requires domain knowledge about process weaknesses, which is not available for processing with process mining. This paper presents an approach to model domain knowledge about weaknesses in business processes to enable their automated and databased detection in event logs with process mining. Thereby, the weakness detection within business process improvement can be conducted more objectively at lower efforts.

Process mining is a technique to model and analyze business process based on traces of activities performed and stored in the database of any information systems being operated by the company i.e. event logs. This paper aims to add literature on the implementation of process mining in warehouse management process. First, extraction of all related activities from LTAK and LTAP tables of SAP Warehouse Management module is conducted. The event log are processed with Heuristic Miner Algorithm in PROM. The output of the mining is the actual business process model. The analysis of the output discover deviation from the standard procedure set by the company with the presence of additional activities and nonstandard flow of materials. The bottleneck analysis shows that the material spent a long time in the high rack and transferred between high racks. The average lead time from material receipt until issued is slightly higher than the target set the company. Further analysis of the issues revealed root-cause of the problems which are insufficient warehouse related capacity such as forklift, racks and staffs to serve incoming materials. Finally, recommendations are provided to deal with the warehouse management issues facing the case companies.