Traditional Process Mining Techniques Research Articles

Analyzing interconnected processes: using object-centric process mining to analyze procurement processes

AbstractThe purchase-to-pay (P2P) process is one of the core business processes in any organization. It ensures the correct and efficient provisioning of materials and services. An efficient P2P process reduces operational costs by ensuring discounts, avoiding late payments, and choosing the optimal supplier for the goods. Process mining techniques help practitioners optimize the execution of P2P processes by analyzing the execution data and providing useful insights. However, existing techniques may result in misleading insights due to many-to-many relationships between business objects, e.g., between orders and invoices in the P2P process. Recently, object-centric process mining techniques have been proposed to avoid the limitations of traditional process mining techniques. In this paper, we present a case study on a real-life P2P process using object-centric process mining techniques. To that end, we adopt the well-known PM$$^{2}$$ 2 process mining project methodology to the object-centric setting and analyze the performance and compliance.

Automated digital twin generation of manufacturing systems with complex material flows: graph model completion

Industry 4.0 determined the emergence of technologies that enable data-driven production planning and control approaches. A digital model can be used to make decisions based on the current state of a manufacturing system, and its efficacy strictly depends on the capability to correctly represent the physical counterpart at any time. Automated model generation techniques such as process mining can significantly accelerate the development of digital twins for manufacturing systems. However, complex production environments are characterized by the convergence of different material and information flows. The corresponding data logs present multiple part identifiers, resulting in the wrong finding of the system structure with traditional process mining techniques. This paper describes the problem of discovering manufacturing systems with complex material flows, such as assembly lines. An algorithm is proposed for the proper digital model generation, aided by the new concept of object-centric process mining. The proposed approach has been applied successfully to two test cases and a real manufacturing system. The results show the applicability of the proposed technique to realistic settings.

Process fragments discovery from emails: Functional, data and behavioral perspectives discovery

Significant research work has been conducted in the area of business process (BP) mining leading to mature solutions for discovering process knowledge. These solutions were generally limited to the analysis of structured event logs generated by BP management systems (BPMS). Given the recent spread of digital workplaces, there have been several initiatives to extend the scope of these analysis to consider other information systems (IS) supporting BP execution informally. More precisely, emailing systems have attracted much attention as they are widely used as alternative tools to collaboratively perform BP activities. However, due to the unstructured nature of email logs data, traditional process mining techniques could not be applied or at least not directly applied. Existing approaches that discovered BP from emails are usually supervised or at least require significant human intervention. They focused on discovering BP with respect to their behavioral perspective (i.e. that defines the conditions for activity execution) while neglecting the discovery of their data perspective (i.e. that defines the informational entities manipulated by BP activities). In addition, they did not studied how emailing systems are used in the context of BP executions. They assume that emailing systems are used in the same way employees use ordinary BPMS. However, employees actually use emails to perform poorly structured BP fragments (i.e. parts) rather than complete and well-structured ones. These BP fragments are not necessary defined in advance as in the case of BPMS. This induces the need to discover BP functional perspective (i.e. that defines what a BP performs and what are its activities). Furthermore, employees use emails with different purposes when talking about BP activities (e.g. information about activity execution, request or planning activity execution, etc.). This results in the occurrence of new event types referring to the purpose of considering activities in emails rather than events referring only to their execution.In this paper, we propose to discover BP from email logs with respect to their functional, data and behavioral perspectives. The paper first formalizes these perspectives. Then, it introduces a completely non-supervised approach for discovering them based on: (i) speech act detection for recognizing the purposes of considering activities in emails, (ii) overlapping clustering of activities to discover their manipulated artifacts (i.e. informational entities), (iii) overlapping clustering of BP elements (i.e. activities, artifacts and activity actors) to discover BP fragments and, (iv) mining sequencing constraints between event types deduced from activities and speech acts to discover behavioral perspective. Our approach is finally validated using the public email dataset Enron.

How Can Interactive Process Discovery Address Data Quality Issues in Real Business Settings? Evidence from a Case Study in Healthcare

The focus of this paper is on how data quality can affect business process discovery in real complex environments, which is a major factor determining the success in any data-driven Business Process Management project. Many real-life event logs, especially healthcare ones, can suffer from several data quality issues, some of which cannot be solved by pre-processing or data cleaning techniques, leading to inaccurate results. We take an innovative Process Mining (PM) approach, termed Interactive Process Discovery (IPD), which combines domain knowledge with available data. This approach can overcome the limitations of noisy and incomplete event logs by putting “humans in the loop”, leading to improved business process modelling. This is particularly valuable in healthcare, where physicians have a tacit domain knowledge not available in the event log, and, thus, difficult to elicit. We conducted a two-step approach based on a controlled experiment and a case study in an Italian hospital. At each step, we compared IPD with traditional PM techniques to assess the extent to which domain knowledge helps to improve the accuracy of process models. The case study tests the effectiveness of IPD to uncover knowledge-intensive processes extracted from noisy real-life event logs. The evaluation has been carried out by exploiting a real dataset of an Italian hospital, involving the medical staff. IPD can produce an accurate process model that is fully compliant with the clinical guidelines by addressing data quality issues. Accurate and reliable process models can support healthcare organizations in detecting process-related issues and in taking decisions related to capacity planning and process re-design.

A Graph-Based Approach to Interpreting Recurrent Neural Networks in Process Mining

Process mining is often used by organisations to audit their business processes and improve their services and customer relations. Indeed, process execution (or event) logs constantly generated through various information systems can be employed to derive valuable insights about business operations. Compared to traditional process mining techniques such as Petri nets and the Business Process Model and Notation (BPMN), deep learning methods such as Recurrent Neural Networks, and Long Short-Term Memory (LSTM) in particular, have proven to achieve a better performance in terms of accuracy and generalising ability when predicting next events in business processes. However, unlike the traditional network-based process mining techniques that can be used to visually present the entire discovered process, the existing deep learning-based methods for process mining lack a mechanism explaining how the predictions of next events are made. This study proposes a new approach to process mining by combining the benefits of the earlier, visually explainable graph-based methods and later, more accurate but unexplainable deep learning methods. According to the proposed approach, an LSTM model is employed first to find probabilities for each known event to appear in the process next. These probabilities are then used to generate a visually interpretable process model graph that represents the decision-making process of the LSTM model. The level of detail in this graph can be adjusted using a probability threshold, allowing to address a range of process mining tasks such as business process discovery and conformance checking. The advantages of the proposed approach over existing LSTM-based process mining methods in terms of both accuracy and explainability are demonstrated using real-world event logs.

Do activity lifecycles affect the validity of a business rule in a business process?

Traditional process mining techniques offer limited possibilities to analyze business processes working in low-predictable and dynamic environments. Recently, to close this gap, declarative process models have been introduced to represent process mining results since they allow for describing complex behaviors as a compact set of business rules. However, in this context, activities of a business process are still considered as atomic/instantaneous events. This is a strong limitation for these approaches because often, in realistic environments, process activities are not instantaneous but executed across a time interval and pass through a sequence of states of a lifecycle. This paper investigates how the existing techniques for the discovery of declarative process models can be adapted when the business process under analysis contains non-atomic activities. In particular, we base our proposed approach on the use of discriminative rule mining to determine how the characteristics of the activity lifecycles in a business process influence the validity of a business rule in that process. The approach has been implemented as a plug-in of the process mining tool ProM and validated on synthetic logs and on a real-life log recorded by an incident and problem management system called VINST in use at Volvo IT Belgium.

A comparative study of dimensionality reduction techniques to enhance trace clustering performances

Process mining techniques have been used to analyze event logs from information systems in order to derive useful patterns. However, in the big data era, real-life event logs are huge, unstructured, and complex so that traditional process mining techniques have difficulties in the analysis of big logs. To reduce the complexity during the analysis, trace clustering can be used to group similar traces together and to mine more structured and simpler process models for each of the clusters locally. However, a high dimensionality of the feature space in which all the traces are presented poses different problems to trace clustering. In this paper, we study the effect of applying dimensionality reduction (preprocessing) techniques on the performance of trace clustering. In our experimental study we use three popular feature transformation techniques; singular value decomposition (SVD), random projection (RP), and principal components analysis (PCA), and the state-of-the art trace clustering in process mining. The experimental results on the dataset constructed from a real event log recorded from patient treatment processes in a Dutch hospital show that dimensionality reduction can improve trace clustering performance with respect to the computation time and average fitness of the mined local process models.