- Data, Statistics and AI for Well-Being of People and Organisations
- A cura di Luigi Fabbris, Alberto Franci, Pietro Renzi
Corruption, well-being and artificial intelligence: A predictive framework for risk measurement
- Fabrizio Sbicca
- © 2026 Author(s) |
- CC BY 4.0
- DOI: 10.36253/979-12-215-1062-1.65
There is now a widely shared consensus that corruption is one of the main obstacles to economic, political, and social development, as it can undermine citizens' trust in institutions, lower the quality of life, and diminish overall well-being. However, to prevent and combat corruption, it is essential to deeply understand this latent phenomenon, which is not easy to measure. A step forward in understanding the phenomenon has been made by the Italian Anti-Corruption Authority, which provides the public with 70 indicators capable of measuring the risk of corruption across the territory. In particular, “Social capital” is a useful composite indicator of the context in which corruption occurs. However, the relationship is also reciprocal: the harm caused by corruption exceeds immediate monetary waste, introducing distortions in both public and private spheres, such as the loss of trust it generates among citizens. For this reason, corruption undermines the very fabric of civil life and can reduce social capital, thereby depressing growth and well-being. Artificial intelligence can help identify patterns and red flags of corruption, as well as other issues such as fraud, conflicts of interest, bid-rigging in public procurement, money laundering, and the infiltration of criminal enterprises. The increasing availability and processing power of large datasets has indeed drawn attention to the potential of developing techniques, such as those based on machine learning, aimed at identifying indicators of criminal behavior for predictive purposes. In this way, artificial intelligence can not only fight corruption directly but also significantly increase knowledge of the phenomenon, also creating a system of indicators aimed at raising collective awareness of the severe social damage caused by corruption. While its prevention and suppression are necessary conditions for reducing the phenomenon, they are not sufficient. The most effective long-term lever is the growth of social capital.
- Keywords:
- Made in Italy,
- Multilabel classification,
- Large Language Models (LLMs),
ANAC, Autorità Nazionale Anticorruzione, Italy
- Banfield E.C. (1958). The Moral Basis of a Backward Society. Free Press DOI: 10.2307/3709468
- Bersch, C., Köbis, N. (2024). Artificial intelligence (AI) (and anti-corruption), in L. De Sousa, S. Coroado (eds.). Elgar Encyclopedia of Corruption and Society, Cheltenham, Edward Elgar, pp. 17-22. DOI: 10.4337/9781803925806.ch05
- De Blasio, G., D'Ignazio, A., Letta, M. (2022). Gotham city. Predicting ‘corrupted’ municipalities with machine learning. Technological Forecasting & Social Change, 184, pp. 1-21. DOI: 10.1016/j.techfore.2022.122016
- Decarolis, F., Giorgiantonio C. (2022). Corruption red flags in public procurement: new evidence from Italian calls for tenders. EPJ Data Science, 11. DOI: 10.1140/epjds/s13688-022-00325-x
- Gnaldi, M., Ponti, B. (2018). Misurare la corruzione oggi. Obiettivi, metodi, esperienze. Milano, Franco Angeli.
- Hastie, T., Tibshirani, R., Friedman, J. (2009). The Elements of Statistical Learning. Data Mining, Inference, and Prediction. Berlin: Springer. DOI: 10.1111/j.1751-5823.2009.00095_18.x
- Istat (2024a). Rapporto Bes 2023.
- Istat (2024b). Rapporto SDGs 2024. Informazioni statistiche per l'Agenda 2030 in Italia.
- James, G., Witten, D., Hastie, T., Tibshirani, R., Taylor. J. (2023). An Introduction to Statistical Learning: with Applications in Python. Berlin, Springer. DOI: 10.1007/978-3-031-38747-0
- Lopez-Iturriaga, F.J., Sanz, I.P. (2018). Predicting public corruption with neural networks: An analysis of Spanish provinces. Social Indicators Research, 140, pp. 975-998. DOI: 10.1007/s11205-017-1802-2
- Mazziotta, M., Pareto, A. (2025). Statistics for Composite Indicators, Berlin, Springer. DOI: 10.1007/978-3-031-97978-1
- OECD (2024). Generative AI for anti-corruption and integrity in government. Taking stock of promise, perils and practice. OECD Artificial Intelligence Papers, 12. DOI: 10.1787/657a185a-en
- Picci, L. (2024). Rethinking Corruption. London: Routledge. DOI: 10.1017/9781009468824
- Putnam, R.D. (1993). Making Democracy Work: Civic Traditions in Modern Italy. Princeton N.J.: Princeton University Press. DOI: 10.1002/ncr.4100820215
- Sbicca, F. (2024a). Intelligenza artificiale e anticorruzione. Rassegna Trimestrale Osservatorio AIR, XV, 4, pp. 39-46. DOI: 10.3280/riv2023-085010
- Sbicca, F. (2024b). La misurazione del rischio di corruzione negli appalti. Rivista Economica del Mezzogiorno, 3-4/2023, pp. 549-600.
- Tulli, A. (2024). Sweeping the dirt under the rug: measuring spillovers of an anti-corruption measure. The Journal of Law, Economics, and Organization, 41(2), pp. 654–699. DOI: 10.2139/ssrn.4081058
- United Nations (2015). 70.1 Transforming our world: the 2030 Agenda for Sustainable Development. Resolution adopted by the General Assembly on 25 September 2015. DOI: 10.18356/e5a72957-en
- UNODC (2023). Statistical Framework to Measure Corruption. Vienna: UNODC.
- Wachs, J., Kertesz, J. (2019). A network approach to cartel detection in public auction markets. Nature, Scientific Reports, 9. DOI: 10.1038/s41598-019-47198-1
- Wachs, J., Fazekas, M., Kertesz, J. (2021). Corruption risk in contracting markets: a network science perspective. International Journal of Data Science and Analytics, 12, pp. 45–60. DOI: 10.1007/s41060-019-00204-1
Informazioni sul capitolo
Titolo del capitolo
Corruption, well-being and artificial intelligence: A predictive framework for risk measurement
Autori
Fabrizio Sbicca
Lingua
Inglese
DOI
10.36253/979-12-215-1062-1.65
Opera sottoposta a peer review
Anno di pubblicazione
2026
Copyright
© 2026 Author(s)
Licenza d'uso
Licenza dei metadati
Informazioni bibliografiche
Titolo del libro
Data, Statistics and AI for Well-Being of People and Organisations
Curatori
Luigi Fabbris, Alberto Franci, Pietro Renzi
Opera sottoposta a peer review
Numero di pagine
420
Anno di pubblicazione
2026
Copyright
© 2026 Author(s)
Licenza d'uso
Licenza dei metadati
Editore
Firenze University Press
DOI
10.36253/979-12-215-1062-1
ISBN Print
979-12-215-1061-4
eISBN (pdf)
979-12-215-1062-1
eISBN (xml)
979-12-215-1063-8
Collana
Applied Statistics Series