Vlerick Repository

Recent Submissions

  • Item
    The influence of emotions and communication style on customer satisfaction and recommendation in a call center context: An NLP-based analysis
    (Elsevier Science Inc., 2025) De Cleen, Thomas; Baecke, Philippe; Goedertier, Frank
    We study the impact of customer sentiment, agent sentiment, and emotional matching (i.e., call center agents matching emotional expressive states of customers) on satisfaction and recommendation intentions in a utilitarian service context. We methodologically contribute by text mining observed data using advanced transformer-based NLP algorithms and compare findings with those of previous survey-based research. An analysis of 25008 call center conversations reveals that positive (vs negative) customer sentiment more strongly impacts satisfaction and recommendation. For recommendation (vs satisfaction) we observe that negative emotional expressions have a relatively stronger weight, albeit less strong than that of positive ones. We find that emotional expressions of call center agents (vs those of clients) have a smaller impact on these outcomes. Emotional matching is observed as beneficial, but not necessarily when faced with negative high-arousal emotional expressions. As conceptual grounding, we refer to theorizing around delight, formality, source credibility, emotional arousal and loss aversion.
  • Item
    A comparison of different clustering algorithms for the project time buffering problem
    (Pergamon Elsevier Science Ltd, 2025) Fangfang, Cao; Servranckx, Tom; Vanhoucke, Mario; He, Zhengwen; School of Management, Xi’an Jiaotong University, Xianning west road 28, 710049 Xi’an, China; Faculty of Economics and Business Administration, Ghent University, Tweekerkenstraat 2, 9000 Ghent, Belgium; UCL School of Management, University College London, 1 Canada Square, London E14 5AA, United Kingdom
    This paper studies the decentralised time buffering problem (TBP) to absorb project risk by building sufficient buffers with the aim of obtaining a stable project schedule. First, the position of the buffers in the project network should be determined and, subsequently, each buffer must be optimally sized. We investigate different activity clustering methods (K-means, rank order, criticality-based and network clustering) to determine the ideal groups of activities to be clustered together and protected by an allocated buffer. The obtained clusters of activities are then inputted in a multi-population multi-factorial evolutionary algorithm (MPMFEA) for creating buffers based on the characteristics of the activities in each cluster. To the best of our knowledge, this is the first study to integrate existing clustering methods into a buffering algorithm in order to optimise the project stability. Previous studies hybridising both methods use a single clustering algorithm (e.g. K-means) that does not use the same information than the buffering algorithm or require more complex (simulation-based) buffering methods. The computational experiments on a large set of artificial instances validate the effectiveness of the proposed MPMFEA for solving the TBP, especially in combination with the network clustering method. Although the generic K-Means method is still considered a viable option for clustering, the more pragmatic clustering methods are more effective. We inform project managers that considering precedence relations between activities during clustering is crucial, but mimicking this behaviour in all clustering methods does not guarantee successful protection of their projects.
  • Item
    How AI can help your company set a budget
    (Harvard Business School Corporation, 2024) Willems, Emma; Stouthuysen, Kristof
    AI has been heralded — and put to use — as a groundbreaking new tool that companies can use in the budgeting process. But even companies that have embraced AI are still struggling with aspects of the budgeting process in today’s complex and rapidly changing business environment. Why is that? When does it make sense to rely on AI, and when does it not? In this article, the authors describe experiments they have conducted on the use of AI in the budgeting process — and conclude that AI can and should replace human managers in tactical tasks, where data-driven decision-making leads to faster and more efficient outcomes, but that in the strategic realm, where long-term planning, market adaptability, and business foresight are critical, human involvement and insight remain indispensable.
  • Item
    Regulatory institutions and cross-country differences in high-growth entrepreneurship rates: A configurational approach
    (Elsevier, 2025) Standaert, Thomas; Collewaert, Veroniek; Vanacker, Tom; Ghent University, Tweekerkenstraat 2, 9000 Gent, Belgium; University of Exeter, Rennes Drive, Exeter EX4 4ST, United Kingdom
    Regulatory institutions are double-edged swords: stricter regulations can improve entrepreneurs' access to key resources but also constrain their discretion. Past research has focused on the individual and/or independent influence of regulatory institutions, calling for stricter regulation or deregulation. However, institutional theory suggests that the full configuration of regulatory institutions, including their possibly complex interactions, drives the trade-off between resource access and the constraints imposed by resource providers. Using an inductive approach and fsQCA analysis, we aim to better understand how configurations of regulatory institutions and contextual conditions influence high-growth entrepreneurship (HGE) rates across European countries. We find that three distinct configurations explain high country-level HGE rates, which include different regulatory institutions that sometimes work in opposing ways and do not necessarily work universally across contexts. Overall, this study deepens research at the nexus of institutional theory and high-growth entrepreneurship.
  • Item
    Does algorithmic trading induce herding?
    (Wiley, 2024) Mianjun Fu, Servanna; Alexakis, Christos; Pappas, Vasileios; Skarmeas, Emmanouil; Verousis, Thanos; Norwich Business School, University of East Anglia, Norwich, UK; Department of Finance and Accounting, Rennes School of Business, Rennes, France; Surrey Business School, University of Surrey, Guildford, UK; Department of Banking and Financial Management, The University of Piraeus, Piraeus, Greece
    Algorithmic trading (AT) plays a major role in the trading activities of developed markets. This research breaks new ground by investigating how AT influences herding behaviour in stock markets. Utilising the implementation of the Markets in Financial Instruments Directive (MiFID II), we show that AT-induced herding is quantitatively 14 times more pronounced compared to herding triggered by non-AT elements. Algorithmic traders herd more when international volatility and market uncertainty are high, revealing a heightened sensitivity to global market signals. However, during periods of high local volatility, AT seems to disregard these fluctuations, indicating an ‘inattention effect’. AT-induced anti-herding is prominent in the volatile aggressive stocks, while no such behaviour is observed in the more stable defensive stocks. The findings carry critical implications for both regulators and market professionals, as we uncover dual behaviours of AT-induced herding and anti-herding in varying market conditions.