Vlerick Repository
Not a member yet
7319 research outputs found
Sort by
A Multi-Module Explainable Artificial Intelligence Framework for Project Risk Management: Enhancing Transparency in Decision-making
No full textThe remarkable advancements in machine learning (ML) have led to its extensive adoption in Project Risk Management (PRM), leveraging its powerful predictive capabilities and data-driven insights that support proactive decision-making. Nevertheless, the “black-box” nature of ML models obscures the reasoning behind predictions, undermining transparency and trust. To address this, existing explainable artificial intelligence (XAI) techniques, such as Local Interpretable Model-agnostic Explanations (LIME), Global Priors-based LIME (G-LIME), and SHapley Additive exPlanations (SHAP), have been applied to interpret black-box models. Yet, they face considerable limitations in PRM, including their inability to model cascading effects and multi-level dependencies among risk factors, suffering from inconsistencies due to random sampling, and failure to capture non-linear interactions in high-dimensional risk data. In response to these shortcomings, this paper proposes the Multi-Module eXplainable Artificial Intelligence framework for Project Risk Management (MMXAI-PRM), a novel approach designed to address the unique demands of PRM. The framework consists of three modules: the Risk Relationship Insight Module (RRIM), which models risk dependencies using a Knowledge Graph (KG); the Risk Factor Influence Analysis Module (RFIAM), which introduces a Conditional Tabular Generative Adversarial Network-aided Local Interpretable Model-agnostic Explanations using Kernel Ridge Regression (CTGAN-LIME-KR) to ensure explanation consistency and handle non-linearity; and the Visualization and Interpretation Module (VIM), which synthesizes these insights into an interpretable, chain-based representation. Extensive experiments demonstrate that MMXAI-PRM delivers more consistent, stable, and accurate explanations than existing XAI methods. By improving interpretability, it enhances trust in AI-driven risk predictions and equips project managers with actionable insights, advancing decision-making in PRM
Bringing Microaggressions From the Shadows to the Spotlight: Unveiling Silencing Mechanisms and Distinct Patterns in Coping
No full textABSTRACT While many organizations work intensively to implement gender equity policies, women's experiences remain heavily marked by covert forms of bias, with microaggressions being the most ubiquitous. Microaggressions (which subtly but persistently manifest prejudice at the behavioral level), persist in workplaces despite growing awareness of their negative impacts. This qualitative study examines why they are often met with silence, exploring the interplay between silencing mechanisms rooted in inequality regimes and individual coping strategies. One hundred twenty‐five participants (three‐quarters of whom were women) shared nearly 700 incidents of microaggressions on an online platform in a Western European setting. Findings highlight five distinct stages individuals cope with microaggressions: ignorance, awareness, hypervigilance, resignation, and psychological control. Each of these coping mechanisms was influenced by structural silencing mechanisms, the individual's understanding of what was happening to them, and the frequency with which they encountered microaggressions. The study underscores how structural inequalities perpetuate microaggressions and their subsequent silencing, emphasizing that the harm of microaggressions goes beyond the initial incident to include the inability to address them effectively. This demonstrates that addressing microaggressions requires a twofold approach: dismantling silencing mechanisms rooted in inequality regimes and empowering individuals with tailored strategies to confront these subtle yet damaging forms of discrimination. This research provides key insights into fostering more inclusive and equitable workplaces
Resource allocation models and heuristics for the multi-project scheduling with global resource transfers and local resource constraints
No full textProposing four models of the RCMPSP with global resource transfers. Improving three classes of priority rule-based heuristics for the new models. Testing and comparing three heuristics with a large amount of priority rules.
Verifying the applicability and good performance of priority rules with a case study.The transfer times and costs of global resources between different projects and the choice of transfer modes significantly affect the multi-project scheduling. This paper investigates four versions of the resource-constrained multi-project scheduling problem with global resource transfers and local resource constraints based on four realistic transfer scenarios, in which the global resource transfer times and costs are considered with a single transfer mode or multiple transfer modes. Three classes of heuristics with huge amount of priority rules are adapted and tested for the new problems. The schedule generation schemes of each class of heuristics are improved from two aspects. On the one hand, resource availability checks are divided into global and local phases due to their different characteristics. On the other hand, resource transfer rules and transfer mode rules are introduced to deal with resource transfer and transfer mode issues, respectively. The three class of heuristics are tested on well-known datasets of the multi-project problem, which are extended with transfer data using a transfer time/cost generation procedure. The numerical experiments first evaluate the performance of a set of priority rules, then effectively apply the priority rule heuristics in the genetic algorithm, and finally compare the performance of the priority rule heuristics with CPLEX on small-scale instances. Additionally, a multi-project case study verifies the applicability and good performance of priority rules that perform well in numerical experiments. Furthermore, the best performing rules are used by two machine learning methods in literature to automatically select the most promising ones
Fifty years of maintenance optimization: Reflections and perspectives
No full textOn the occasion of the 50th anniversary of the Association of European Operational Research Societies (EURO), we share our perspectives and reflections on maintenance research. We review the main methods and techniques for optimizing when and what to maintain, providing concrete examples as illustrations. We also discuss the optimization of the logistics support system surrounding the act of maintenance. In doing so, we highlight the multidisciplinary nature of maintenance research and its interface with other domains, such as spare parts inventory management, production scheduling, and transportation planning. We support our reflections with basic text-mining analyses of the archive of the European Journal of Operational Research, the journal published in collaboration with EURO. With this paper, we introduce interested researchers to maintenance optimization and share opportunities to close the gaps between the current state of research and real-world needs
The effect of proactive job search motivation profiles on job search quality in the school-to-work transition
No full textPurpose This research examines proactive motivation profiles among young graduates in their job search process during the school-to-work transition, and their relation to the job search quality process (JSQP). Additionally, we investigate the effect of proactive personality on the movement between different profiles over two time points. Design/methodology/approach We collected data from 814 young Vietnamese graduates at two time points, and used a person-centered approach and random intercept latent transition analysis in analyzing the data. Findings Four distinct profiles combined different levels of job-search self-efficacy, job-search outcome expectations and perceived financial need at both time points. The most beneficial profile in terms of JSQP, “optimism pioneers”, was the least common profile. The “balanced pursuers” profile was the largest and the most stable group over time. A proactive personality positively influenced the within-person movement between profiles over time. Originality/value Our findings support the effectiveness of a person-centered approach in analyzing the motivational attitudes of young graduates during the complex and time-consuming job-search process after graduation
Academy of Management Proceedings
No full textThis paper investigates the relationship between corporate cultural diversity and long-term financial performance, focusing on the moderating role of employee ownership. We argue that corporate cultural diversity, the coexistence of multiple distinct values within an organization, allows firms to better adapt and pivot their strategic focus benefiting firms’ long-term financial performance. However, as corporate cultural diversity may also promote misunderstandings and conflicts among employees, we suggest that firms with higher levels of employee ownership are better equipped to capitalize on the advantages of corporate cultural diversity. Employee ownership may help to mitigate the potential negative effects of corporate cultural diversity as an increased sense of ownership facilitates to solve arising conflicts. Drawing on a dataset of S&P 1500 firms, our findings reveal that companies benefit from more corporate cultural diversity only in the context of high levels of employee ownership. These findings highlight the dynamic between corporate cultural diversity and ownership structures, offering insights into how firms can leverage corporate cultural diversity to strengthen long-term performance
Trust in AI: Building Human-Tech Collaboration That Works
No full textArtificial Intelligence (AI) is reshaping how organisations make decisions, streamline operations and innovate. But to fully realise its value, trust between people and intelligent systems is essential. In a recent Vlerick Business School webinar, Professors Karlien Vanderheyden and researcher Ignace Decroix shared insights from their research on trust, AI and the human factor in digital transformation. The session explored how AI is already part of many decision-making processes, and how organisations can foster collaboration between people and technology to achieve better outcomes
Pay fairness: Achieving trust and transparency
No full textPay transparency is a compliance necessity, but the psychological dimensions of rewards fairness are just as crucial. Learn about the three critical dimensions underlying pay fairness and review a checklist of key rewards communication factors
Mind the ESG valuation gap - A chatGPT routine to assess ESG value integration in annual reports
No full textThis white paper exposes the gap between sustainability talk and true value creation. Discover why most disclosures overwhelm rather than inform, and how to fix it. Prof Verousis introduces a ChatGPT-powered tool that scans annual reports for real ESG integration. It tests claims against six value-linked pillars: strategy, risk, opportunity, valuation, governance, and disclosure. The result? A clear, comparable ESG integration score that cuts through greenwash. Use it to benchmark peers, track progress, and pinpoint where value is at risk. It works for investors, analysts, executives, and even companies checking their own narrative. Case studies show the wide gap between leaders and laggards. The tool links ESG to cash flow, capital costs, and growth potential. It’s free, scalable, and ready to deploy. Transform ESG from a checkbox to a valuation driver
What drives patient cost variability in psoriasis care: a single centre study
No full textBackgroundPsoriasis a chronic inflammatory skin disease, poses a substantial economic burden on healthcare systems globally. This study examines psoriasis consultations from the provider’s perspective within a dermatology department, aiming to generate detailed cost data to support value-based care. Specifically, it investigates the drivers of consultation-level cost variability, explores opportunities for efficiency, and also estimates one-year treatment costs to inform the development of bundled payment models. The goal is to highlight the importance of patient cost transparency and improving cost structures in chronic disease settings.MethodsUsing Time-Driven Activity-Based Costing (TD-ABC), treatment costs associated with nurses, doctors, and total visits for 127 patients with mild and moderate forms of psoriasis were measured. Financial data was collected in collaboration with the hospital’s financial department. During consultations, nurses and physicians recorded time and patient-related information. Additional or missing details were retrieved from patient medical files. Descriptive analyses assessed mean costs and variability by patient and disease characteristics. Independent variables: therapy type, patient status (new vs. returning), comorbidities, and treatment changes, were stratified to compare cost differences across groups.ResultsMean consultation costs were €55, with a minimum and maximum of €25 and €110. New patients incurred 40% higher costs than returning ones, mainly due to longer interactions with nurses and physicians. Key cost drivers for a total consultation included patient status, personality traits, nurse experience, and therapy switches. Physician consultations were particularly impacted by treatment changes and patient engagement levels. Annual treatment costs varied substantially by medication type: topical treatments averaged €325 per year, systemic treatments €1,353, and biological therapies €11,920, highlighting the significant impact of medication choice on overall expenses.ConclusionsThis study highlighted substantial variability in consultation and yearly treatment costs for psoriasis patients. These findings emphasized the critical need for detailed cost data to optimise departmental workflows, support efficient resource allocation, and inform the design of equitable bundled payment models. Improving cost transparency was shown to strengthen clinical and financial decision-making. Future research was recommended to explore the cost implications of comorbidities and to extend benchmarking efforts across dermatology settings to guide system-wide improvements in care delivery and sustainability.(Flemish Government