Customer churn is a problem virtually all companies face, and the ability to predict it reliably can be a cornerstone for successful retention campaigns. In this study, we propose an approach to customer churn prediction in non-contractual B2B settings that relies exclusively on invoice-level data for feature engineering and uses multi-slicing to maximally utilize available data. We cast churn as a binary classification problem and assess the ability of three established classifiers to predict it when using different churn definitions. We also compare classifier performance when different amounts of historical data are used for feature engineering. The results indicate that robust models for different churn definitions can be derived by using invoice-level data alone and that using more historical data for creating some of the features tends to lead to better performing models for some classifiers. We also confirm that the multi-slicing approach to dataset creation yields better performing models compared to the traditionally used single-slicing approach.

This study investigated the crucial factors for measuring the success of the information system used in the e-learning process, considering the transformations in the work environment. This study was motivated by the changes caused by COVID-19 witnessed after the shift to fully online learning environments supported by e-learning systems, i.e., learning emphasized with information systems. Empirical research was conducted on a sample comprising teaching staff from two European universities: the University of Novi Sad, Faculty of Technical Sciences in Serbia and the Polytechnic Institute of Castelo Branco in Portugal. By synthesizing knowledge from review of the prior literature, supported by the findings of this study, the authors propose an Extended Information System Success Measurement Model—EISSMM. EISSMM underlines the importance of workforce agility, which includes the factors of proactivity, adaptability, and resistance to change, in the information system performance measurement model. The results of our research provide more extensive evidence and findings for scholars and practitioners that could support measuring information system success primarily in e-learning and other various contextual settings, highlighting the importance of people’s responses to work environment changes.

As a plan, Industry 4.0 encourages manufacturing companies to switch from conventional Product-Service Systems to Digital Product-Service Systems. Systems of goods, services, and digital technologies known as “Digital Product-Service Systems” are provided to improve consumer satisfaction and business success in the marketplace. Previous studies have looked into various elements of this area for industrial companies and academic institutions. Digital Product-Service Systems’ overall worth and expected course of growth are still ignored. The authors use bibliometric analysis to organize the body of prior knowledge in this discipline and, more significantly, to identify areas for further study in order to cover the literature deficit. The results of the most esteemed authors, nations, and sources in the subject were given by this study. The findings also show that terms like digitization, sustainability, and business have grown in popularity over the previous year. This study also offered insight into how Industry 5.0, a new manufacturing strategy, would include Digital Product-Service Systems. Finally, the findings of this research demonstrate three new service orientations, namely resilient, sustainable, and human-centric, in manufacturing firms.

Research exploring quality management, knowledge management, and innovations in organizations has received significant attention from academics worldwide, providing different insights. Innovation has been widely seen as an essential organizational performance driver. This study aims to accentuate the importance of quality management and knowledge management and their direct, mediating, and total effect on an organization’s process innovations. The double-reflective second-order construct model was analyzed following the most recent methodology guidelines. Eventually, partial least squares structural equation modeling (PLS-SEM) was used to test the research hypotheses and investigate the relations between the latent factors. The results from 264 Serbian companies that implemented ISO 9001 standard point to quality management’s direct effect on process innovations and knowledge management’s mediating effect on process innovation.

Business processes present a core of business organizations from the occurrence of process view on the organization. With the advent of globalization and frequent economic changes, there is an increased level of complexity of enterprise-environment relations, and consequently a raising need for managing these processes. Business process modelling is a necessity and prerequisite for business process management and therefore many business process technices and languages were developed. In the past five decades, business processes are managed through automated systems and these business process modelling techniques have been used for the purpose of documentation of information systems requirements and needs. This paper presents one solution for modelling of production planning business process in a mid-sized organization in Serbia, utilizing UML class diagram.