The chapter explores to what extent artificial intelligence (AI) can facilitate the assessment of insurance contracts in light of the applicable provisions of contract law. An existing AI system for the analysis of consumer contracts, developed as part of the Claudette project, provides the starting point for this investigation. While this system was shown to be successful in the domain of online terms of service, it remains to be verified whether a similar performance can be obtained in the insurance sector, in which detailed and fragmented rules apply. With this in mind, the chapter presents a prototype system seeking to automate the identification and classification of (potentially) defective clauses in standardised B2B insurance contracts, developed as part of the Scudo project, and discusses its potential and limits.
Jabłonowska, A., Lagioia, F., Liepiņa, R., Micklitz, H., Sartor, G. (2025). Automating Compliance Assessment of Insurance Contracts Using AI: Promises and Challenges. Cham : Springer-Verlag Italia s.r.l. [10.1007/978-3-031-96496-1_7].
Automating Compliance Assessment of Insurance Contracts Using AI: Promises and Challenges
Lagioia, Francesca
;Sartor, Giovanni
2025
Abstract
The chapter explores to what extent artificial intelligence (AI) can facilitate the assessment of insurance contracts in light of the applicable provisions of contract law. An existing AI system for the analysis of consumer contracts, developed as part of the Claudette project, provides the starting point for this investigation. While this system was shown to be successful in the domain of online terms of service, it remains to be verified whether a similar performance can be obtained in the insurance sector, in which detailed and fragmented rules apply. With this in mind, the chapter presents a prototype system seeking to automate the identification and classification of (potentially) defective clauses in standardised B2B insurance contracts, developed as part of the Scudo project, and discusses its potential and limits.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


