Improving Software Maintenance Using Process Mining and Predictive Analytics

Process mining consists of mining event logs generated from business process execution supported by Information Systems (IS). Process mining of software repositories has diverse applications because vast data is generated during Software Development Life Cycle (SDLC) and archived in IS such as Version Control System (VCS), Peer Code Review (PCR) System, Issue Tracking System (ITS), and mail archives. There is need to explore its applications on different repositories to aid managers in process management. We conduct two phase surveys and interviews with managers in a large, global, IT company. The first survey and in-person interviews identify the process challenges encountered by them that can be addressed by novel applications of process mining. We filter, group and abstract responses formulating 30 generic problem statements. On the basis of process mining type, we classify identified problems to eight categories such as control analysis, organizational analysis, conformance analysis, and preventive analysis. The second survey asks distinct participants the importance of solving identified problems. We calculate proposed Net Importance Metric (NIM) using 1262 ratings from 43 participants. Combined analysis of NIM and first survey responses reveals that the problems mentioned by few practitioners in first survey are considered important by majority in the second survey. We elaborate on possible solutions and challenges for most frequent and important problems. We believe solving these validated problems will help managers in improving project quality and productivity.

In the dynamic business environment, leveraging predictive analytics for sales optimization and business development has become crucial for achieving sustained growth. As the e-commerce landscape continues to evolve, many e-businesses must harness the power of predictive analytics to anticipate sales trends and optimize business development strategies. This paper explores the application of sales predictive analytics, focusing on its role in forecasting sales, optimizing resource allocation, and enhancing customer relationship management. The application of predictive analytics in sales forecasting in online marketplace platforms is also explored, through the examination of various predictive models using real-world case studies. By exploring various methodologies and tools, the study illustrates how predictive analytics can be integrated into e-businesses' operations to drive growth, and enhance decision-making, highlighting the transformative potential of analytics in making data-driven decisions, ultimately fostering sustainable growth and competitive advantage. Through the analysis of historical sales data, consumer behaviour patterns, and market trends, predictive analytics provides actionable insights that are crucial for strategic planning and operational efficiency. The paper also addresses challenges and best practices for implementing predictive analytics into the business process of e-businesses. ‍

PurposeProcess mining has emerged in the last decade as one of the most promising tools to discover and understand the actual execution of processes. This paper addresses the application of process mining techniques to analyze the performance of automatic guided vehicles (AGVs) in one of the Body in White circuits of the factory that Stellantis has in Vigo, Spain.Design/methodology/approachStandard process mining discovery and conformance algorithms are applied to analyze the different AGV execution paths, their lead times, main sources and identify any unexpected potential situations, such as unexpected paths or loops.FindingsResults show that this method provides very useful insights which are not evident for logistics technicians. Even with such automated devices, where the room for decreased efficiency can be apparently small, process mining shows there are cases where unexpected situations occur, leading to an increase in circuit times and different variants for the same route, which pave the road for an actual improvement in performance and efficiency.Originality/valueThis paper provides evidence of the usefulness of applying process mining in manufacturing processes. Practical applications of process mining have traditionally been focused on processes related to services and management, such as order to cash and purchase to pay in enterprise resource planning software. Despite its potential for use in industrial manufacturing, such contributions are scarce in the current state of the art and, as far as we are aware of, do not fully justify its application.

This research recognizes the limitation and challenges of adapting and applying Process Mining as a powerful tool and technique in the Hypothetical Software Architecture (SA) Evaluation Framework with the features and factors of lightweightness. Process mining deals with the large-scale complexity of security and performance analysis, which are the goals of SA evaluation frameworks. As a result of these conjectures, all Process Mining researches in the realm of SA are thoroughly reviewed, and nine challenges for Process Mining Adaption are recognized. Process mining is embedded in the framework and to boost the quality of the SA model for further analysis, the framework nominates architectural discovery algorithms Flower, Alpha, Integer Linear Programming (ILP), Heuristic, and Inductive and compares them vs. twelve quality criteria. Finally, the framework’s testing on three case studies approves the feasibility of applying process mining to architectural evaluation. The extraction of the SA model is also done by the best model discovery algorithm, which is selected by intensive benchmarking in this research. This research presents case studies of SA in service-oriented, Pipe and Filter, and component-based styles, modeled and simulated by Hierarchical Colored Petri Net techniques based on the cases’ documentation. Process mining within this framework deals with the system’s log files obtained from SA simulation. Applying process mining is challenging, especially for a SA evaluation framework, as it has not been done yet. The research recognizes the problems of process mining adaption to a hypothetical lightweight SA evaluation framework and addresses these problems during the solution development.

With the technology emerging more and more possible applications of process mining in healthcare become apparent. In most cases the goal of applying process mining to the healthcare domain is to find out what actually happened and to deliver a concise assessment of the organizational reality by mining the event logs of health information systems. To develop medical guidelines or patient pathways considering economic aspects and quality of care, a comparative analysis of different existing approaches is useful (e.g. how different hospitals execute the same process in different ways). This work discusses how to use existing process mining techniques for comparative analysis of healthcare processes and presents an approach based on the L* life-cycle model.

Care pathways are widely used as evidence-based clinical governance tools to enhance the quality of care of groups of patients with a specific clinical problem and optimize the use of resources. However, it is often the case that there are differences between the recommended care pathway and the actual clinical practice. Recently, Process Mining (PM) techniques, a family of data-driven techniques from computer science that uses logs (execution traces) of a system to reason about its underlying process, have been applied in the healthcare context to map and analyze real-world practice patterns. In particular, PM helps to discover and analyze the sequence of activities, to highlight variances and possible sub-optimal management of the clinical paths in order to improve care quality and reduce the inefficient allocation of resources. Using the breast cancer pathway as a case study example, this study aims to describe the application of PM to administrative healthcare data of public hospitals of the Tuscany Region (Italy) and to offer insights about strengths and limitations in data management, information creation, and interpretation to support decision-making. The study revealed variations in the management of breast cancer care pathways across different public healthcare providers and with respect to the recommended guidelines. Key findings include instances of service duplication, delays, and bottlenecks, particularly in the diagnostic phase. The analysis also highlighted variations in healthcare costs, driven by differences in the frequency and types of diagnostic exams or visits performed. The findings have practical implications for enhancing the efficiency and quality of breast cancer care and provide a practical example of how the methodology can be applied to other healthcare contexts for similar benefits.

The last-mile delivery problem is one of the most complex and resource-intensive aspects of modern logistics, especially within the growing e-commerce sector. As online shopping continues to expand, companies are under immense pressure to deliver goods more quickly, efficiently, and at lower costs, all while meeting the demands of increasingly time-sensitive customers. This has created a need for innovative solutions that can tackle challenges related to dynamic traffic patterns, fluctuating customer preferences, and operational constraints such as vehicle capacities and delivery windows. In response to these challenges, this paper explores the application of predictive analytics as a tool for optimizing last-mile delivery routes in real-time.The study begins by identifying the core challenges inherent in last-mile logistics, particularly in the U.S. e-commerce landscape, where the cost of last-mile delivery can represent up to 53% of total shipping costs. With traffic congestion, unpredictable customer availability, and delivery time constraints posing significant hurdles, conventional static route planning models often fall short. In this paper, predictive analytics is proposed as a solution to these challenges, utilizing real-time data to inform more efficient routing decisions. By processing vast amounts of real-time traffic data, customer preferences, and delivery constraints, predictive models can offer a more flexible and responsive approach to last-mile delivery.The research then presents a comprehensive literature review of existing route optimization methods, such as the traditional Vehicle Routing Problem (VRP) and its extensions, including VRP with Time Windows (VRPTW), Dynamic VRP (DVRP), and Capacitated VRP (CVRP). While these models have proven useful, their limitations are exposed when faced with real-time operational complexities in the e-commerce sector. Therefore, this study introduces an advanced dynamic routing model that integrates machine learning algorithms—such as decision trees and neural networks—with traditional VRP frameworks. These machine learning models, trained on historical data, are capable of predicting future traffic patterns, customer behavior, and delivery time windows.A case study is conducted using data from U.S.-based e-commerce companies to demonstrate the practical application of predictive analytics in optimizing last-mile delivery. The case study outlines how predictive models are used to dynamically adjust delivery routes based on real-time conditions, leading to significant improvements in efficiency, cost savings, and customer satisfaction. Key performance indicators such as delivery times, fuel consumption, and vehicle utilization are examined before and after the implementation of the predictive models, with the results showing a reduction in delivery time by 20% and fuel costs by 15%, alongside improved on-time delivery rates.The paper concludes by presenting the proposed dynamic route optimization model as a solution that combines the flexibility and responsiveness of predictive analytics with the robust framework of traditional VRP models. Through the integration of machine learning, real-time data processing, and dynamic routing, the model is shown to significantly improve last-mile delivery efficiency. This study's findings highlight the potential for predictive analytics to revolutionize the logistics industry, particularly in the high-demand e-commerce sector, where quick and reliable delivery is paramount. The research suggests that as e-commerce continues to grow, predictive analytics will play an increasingly critical role in ensuring that last-mile delivery is both cost-effective and responsive to the evolving needs of consumers.

Logistics processes are characterized by a high degree of complexity, dynamics, diversity, and human-centricity. The reasons are manifold - product complexity, unexpected events (such as strikes, weather conditions, accidents, etc.), and the high number of participants in the logistics processes. Improving our understanding and making the process more transparent can help to avoid risks and increase performance. The main purpose of this paper is to show a practical application of process mining in the specific domain of seaport terminals. We apply process mining techniques to real port data and discover process models without a priori knowledge. A new framework for the improvement of process mining results using context-aware information in terms of seaports is proposed.

Business process management is a popular approach that has caught the attention of several researchers over the years. BPM has been extended to Business Process Intelligence in order to add more intelligence to managing business processes. Process Mining is one of the emerging areas of Business Process Intelligence, which aims to automatically discover, verify and improve business processes. Nowadays, the emergence of smart environment. The data that occurs in this environment are more varied and are kind of unstructured data. In this sense, applying process mining, to analyze processes in a smart context is a challenging task, since the process mining techniques relies on a structured event log. In this paper, we present a comparative study of existing approaches on applying process mining techniques in smart BPM, as a first step towards developing a new approach to discover and analyze business processes from sensor data perspective.KeywordsProcess Mining (PM)Smart environmentsSensor logSmart BPM

The recent COVID-19 outbreak has caused a high threat to the medical sciences across the world. About 39,596,858 confirmed cases and 1,107,374 deaths were witnessed as of 18 October 2020 by the World Health Organization. Although several strategies have been adopted for drug discovery, a promising drug/vaccine has not been developed. Conventional drug discovery is a time-consuming and expensive process and therefore adopting computational predictions would contribute to quicker and cost-effective drug discovery. Computational intelligence has played a significant part during the pandemic by designing applications for tracking of the community spread of the infection, processing and analyzing chest images and also developing computational tools and software for predictive analysis that contribute to the drug discovery channel. In this chapter, we provide a brief overview of the applications of computational intelligence and predictive analytics in screening potential lead molecules against COVID-19 with an emphasis on the drug repurposing. Bioinformatic tools and software are associated with the molecular targets, especially protein structure prediction, energy minimization of the predicted structures, binding site predictions, different ligand databases, virtual screening based on drug likeliness, pharmacokinetic and toxicity predictions, molecular docking and interaction modeling analysis along with various computational biology tools and software. This chapter also highlights the predictions of the binding potential of the few antibiotics that can be repurposed against the severe acute respiratory syndrome-coronavirus-2 targets by several computational biology tools and resources. Therefore, this chapter certainly enlightens with various approaches to computational intelligence and predictive analytics that would aid in fastening the process of drug discovery.

Predictive Analytics in SAP for Demand-Driven Inventory Optimization is a crucial strategy for enhancing inventory management in dynamic supply chain environments. By integrating advanced analytics and machine learning capabilities, SAP enables businesses to forecast demand patterns, optimize stock levels, and reduce operational costs. This approach empowers organizations to predict fluctuations in demand with greater accuracy, ensuring that inventory levels are adjusted in real-time to meet customer needs while minimizing excess stock. The application of predictive analytics helps to streamline replenishment processes, reduce stockouts, and improve overall customer satisfaction. This paper explores the role of SAP's predictive analytics tools in optimizing inventory through demand-driven strategies, providing businesses with a competitive edge in an increasingly complex global marketplace.

Energy efficiency plays a crucial role in the field of industrial automation, particularly in relation to conveyor belt systems that operate continuously in various sectors, including mining, logistics, and manufacturing. Smart Industrial Components (SIC) are required to process, manage, and produce a substantial amount of different types of IIOT (Industrial Internet of Things) data. This historical data is the main source for analysing the current and future conditions of the components. In this paper, a predictive analytics algorithm is proposed to analyse the trend of real-time and future power consumption. The proposed algorithm seamlessly combines generative AI with IIoT data to enhance predictive modelling capabilities. This study highlights key challenges, methodologies, and future directions in leveraging AI-driven analytics for industrial energy management, as well as investigates the application of predictive data analytics for conveyor belt systems focusing on two key aspects: (1) historical data analysis to monitor the current condition of the conveyor belt system and (2) the use of generative AI for future prediction essential for analysing future trends of power consumption running at the specific condition.

Process mining techniques and applications – A systematic mapping study

In healthcare facilities, processes are not always carried out under the expected methods. The variation in practice leads to lesser quality treatments and greater costs. Within a single visit, patients are now likely to interact with multiple departments, healthcare providers, and Health Information Systems (HIS). Because of these events, information is frequently dispersed, not normalized, and incoherent, creating several barriers to overview processes and audit their quality. Process mining can be a useful tool for getting over some of these obstacles. We designed a procedure to automatically apply process mining techniques using the HL7 standard, which is used for exchanging information between HIS, as a source of event logs. Our work provides a way for pooling HL7 messages from a unified repository of a healthcare institution and provides a pipeline to apply process mining methods to create insights relative to the healthcare processes that are implemented. We show a few diagrams to demonstrate the tool’s potential as a process formalization and analysis tool. We concluded that using HL7 messages as a proxy for processes that involve several HIS is a way to easily provide process mining capabilities to an organization.

The paper presents a summary of the PhD thesis 'Perspectives on Improving Software Maintenance' by F. Niessink (2000). The research described in this thesis investigates process improvement of software maintenance from two perspectives: measurement-based improvement and maturity-based improvement.