Arno De Caigny
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Arno De Caigny has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Kristof Coussement
IESEG School of Management, Univ. Lille, CNRS, UMR 9221 ‐ LEM‐ Lille Economie Management Lille France
11 shared publications - Koen W. De Bock
Audencia Business School, Nantes, France
5 shared publications - Jochen De Weerdt
KU Leuven
2 shared publications - Matthijs Meire
IESEG School of Management, UMR 9221-LEM-Lille Economie Management, Univ. Lille, CNRS, Lille, France
2 shared publications Annelies Raes
1 shared publication- C. Gary Mena
School of Business and Economics, Humboldt-University of Berlin, Berlin, Germany
1 shared publication
Latest Publications
- Open Access
- 10 July 2026
- Published by Springer Nature in Journal of Business Ethics
- p. 1-21
Diversity and Inclusion in Social Media Communication: An Empirical Study of Engagement in the Football Context
Different stakeholders, especially customers, increasingly expect organizations to communicate about diversity and inclusion (D&I) on social media. However, the relationship between D&I content and social media engagement remains unclear. This empirics-first study in a football context investigates how the presence of D&I dimensions in social media content relates to volume of engagement. In the first study phase, we conduct interviews with 11 experts, based on which we uncover seven D&I dimensions key to social media communication: age, gender, body and mind, sexual orientation, race and ethnicity, social class and social status, and religion and cultural diversity. The second phase is based on quantitative analyses of 6006 social media posts from 9 football associations across Facebook and Instagram. The posts were coded by a diverse set of human annotators for the perceived presence of each of the seven D&I dimensions. We find negative relationships between the presence of D&I dimensions and volume of engagement in general, yet we also find that the relationship patterns differ across individual D&I dimensions: negative associations for age and gender diversity, but positive associations for race diversity. Our granular approach can explain why prior research, either taking an aggregate or a piecemeal approach, has been inconclusive. Using Social Identity Theory as a theoretical lens, we explore identification, through value congruence and based on identity cues, as potential explanations for our findings. We elaborate on the theoretical and ethical contributions of our findings across both study phases, underscoring the context and topic’s unique position for producing relevant insights.
- 10 July 2026
- Published by Springer Nature in Journal of Business Ethics
- p. 1-21
Open AccessDiversity and Inclusion in Social Media Communication: An Empirical Study of Engagement in the Football Context
Different stakeholders, especially customers, increasingly expect organizations to communicate about diversity and inclusion (D&I) on social media. However, the relationship between D&I content and social media engagement remains unclear. This empirics-first study in a football context investigates how the presence of D&I dimensions in social media content relates to volume of engagement. In the first study phase, we conduct interviews with 11 experts, based on which we uncover seven D&I dimensions key to social media communication: age, gender, body and mind, sexual orientation, race and ethnicity, social class and social status, and religion and cultural diversity. The second phase is based on quantitative analyses of 6006 social media posts from 9 football associations across Facebook and Instagram. The posts were coded by a diverse set of human annotators for the perceived presence of each of the seven D&I dimensions. We find negative relationships between the presence of D&I dimensions and volume of engagement in general, yet we also find that the relationship patterns differ across individual D&I dimensions: negative associations for age and gender diversity, but positive associations for race diversity. Our granular approach can explain why prior research, either taking an aggregate or a piecemeal approach, has been inconclusive. Using Social Identity Theory as a theoretical lens, we explore identification, through value congruence and based on identity cues, as potential explanations for our findings. We elaborate on the theoretical and ethical contributions of our findings across both study phases, underscoring the context and topic’s unique position for producing relevant insights.
- 3 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Innovation in customer scoring for the financial services industry
L’innovation dans la notation des clients pour le secteur des services financiers: Cette thèse améliore la notation des clients. L’évaluation des clients est importante pour les entreprises dans leurs processus de prise de décision parce qu'elle aide à résoudre des problèmes de gestion clés tels que le choix des clients à cibler pour une campagne de marketing ou l'analyse des clients qui sont susceptibles de quitter l'entreprise. La recherche effectuée dans le cadre de cette thèse apporte plusieurs contributions dans trois domaines de la littérature sur la notation des clients. Premièrement, de nouvelles sources de données sont utilisées pour évaluer les clients. Deuxièmement, la méthodologie pour passer des données aux décisions est améliorée. Troisièmement, la prédiction des événements courants du client est proposée comme une nouvelle application de la notation des clients. Tous les résultats présentés dans cette thèse sont issus de données réelles et sont non seulement d'une grande valeur académique, mais aussi d'une grande pertinence commerciale.
- 3 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Innovation in customer scoring for the financial services industry
L’innovation dans la notation des clients pour le secteur des services financiers: Cette thèse améliore la notation des clients. L’évaluation des clients est importante pour les entreprises dans leurs processus de prise de décision parce qu'elle aide à résoudre des problèmes de gestion clés tels que le choix des clients à cibler pour une campagne de marketing ou l'analyse des clients qui sont susceptibles de quitter l'entreprise. La recherche effectuée dans le cadre de cette thèse apporte plusieurs contributions dans trois domaines de la littérature sur la notation des clients. Premièrement, de nouvelles sources de données sont utilisées pour évaluer les clients. Deuxièmement, la méthodologie pour passer des données aux décisions est améliorée. Troisièmement, la prédiction des événements courants du client est proposée comme une nouvelle application de la notation des clients. Tous les résultats présentés dans cette thèse sont issus de données réelles et sont non seulement d'une grande valeur académique, mais aussi d'une grande pertinence commerciale.
- 24 March 2026
- Published by Taylor & Francis in Journal of Advertising Research
- Vol. 66 (2) , 190-198
Is Similarity in Advertising a Double-Edged Sword? The Role of AI-Generated Faces
- 24 March 2026
- Published by Taylor & Francis in Journal of Advertising Research
- Vol. 66 (2) , 190-198
Is Similarity in Advertising a Double-Edged Sword? The Role of AI-Generated Faces
- 11 February 2025
- Published by Springer Nature in Annals of Operations Research
- Vol. 346 (3) , 2401-2421
Investigating the impact of undersampling and bagging: an empirical investigation for customer attrition modeling
- 11 February 2025
- Published by Springer Nature in Annals of Operations Research
- Vol. 346 (3) , 2401-2421
Investigating the impact of undersampling and bagging: an empirical investigation for customer attrition modeling
- 25 January 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 323 (2) , 609-625
From collaborative filtering to deep learning: Advancing recommender systems with longitudinal data in the financial services industry
- 25 January 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 323 (2) , 609-625
From collaborative filtering to deep learning: Advancing recommender systems with longitudinal data in the financial services industry
- 2 October 2024
- Published by Elsevier in Decision Support Systems
- Vol. 187
Improved decision-making through life event prediction: A case study in the financial services industry
- 2 October 2024
- Published by Elsevier in Decision Support Systems
- Vol. 187
Improved decision-making through life event prediction: A case study in the financial services industry
- 6 April 2024
- Published by Elsevier in Decision Support Systems
- Vol. 181
Hybrid black-box classification for customer churn prediction with segmented interpretability analysis
- 6 April 2024
- Published by Elsevier in Decision Support Systems
- Vol. 181
Hybrid black-box classification for customer churn prediction with segmented interpretability analysis
- 20 January 2024
- Published by Elsevier in European Journal of Operational Research
- Vol. 315 (2) , 691-702
Industry-sensitive language modeling for business
- 20 January 2024
- Published by Elsevier in European Journal of Operational Research
- Vol. 315 (2) , 691-702
Industry-sensitive language modeling for business
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Coupling Neural Networks Between Clusters for Better Personalized Care
Personalized healthcare powered by machine learning (ML) is at the forefront of modern medicine, promising to optimize treatment outcomes, reduce adverse effects, and improve patient satisfaction. However, simple ML models generally lack the complexity to accurately model individual characteristics, while powerful ML models require large amounts of data, which are often unavailable in the healthcare domain. We address this problem with cluster-level personalization. In this method, similar patients are grouped into clusters and a local ML model is trained for each cluster. Since the amount of patient data to train ML models naturally decreases for each cluster, we introduce a novel objective function called "coupling" that allows information to be shared between clusters, so that smaller clusters can also benefit from information from larger clusters, thereby improving patient outcome prediction. Our method provides a compromise between a single global model for all patients and completely independent local cluster models. We show that coupling leads to statistically significant improvements on a simulated and a real-world dataset in the context of diabetes.
- 1 January 2024
- Published by HICSS Conference Office
Open AccessCoupling Neural Networks Between Clusters for Better Personalized Care
Personalized healthcare powered by machine learning (ML) is at the forefront of modern medicine, promising to optimize treatment outcomes, reduce adverse effects, and improve patient satisfaction. However, simple ML models generally lack the complexity to accurately model individual characteristics, while powerful ML models require large amounts of data, which are often unavailable in the healthcare domain. We address this problem with cluster-level personalization. In this method, similar patients are grouped into clusters and a local ML model is trained for each cluster. Since the amount of patient data to train ML models naturally decreases for each cluster, we introduce a novel objective function called "coupling" that allows information to be shared between clusters, so that smaller clusters can also benefit from information from larger clusters, thereby improving patient outcome prediction. Our method provides a compromise between a single global model for all patients and completely independent local cluster models. We show that coupling leads to statistically significant improvements on a simulated and a real-world dataset in the context of diabetes.