The well renown AUTOMATING SOCIETY REPORT 2020 discusses the ongoin research Predicitve Justice by the LIDER Lab of the Sant'Anna School in collaboration with EMbeDS, The “Predictive Justice” approach allows users to access and analyze — through machine learning techniques — the corpus of rulings by the judiciary of the affiliated Courts.
The purpose of this is to extract meaningful information for further processing, starting with the identification of common trends in jurisprudence focused on a specific subject matter (e.g., past judgments on a certain typology of crime or around similar court cases). This would provide a benchmark against which each human judge might assess the case before him or her, and easily check for consistency with previous rulings in analogous situations. Ideally, it might even help characterize interpretative consistency of legal rules -- as opposed to arbitrariness of judges -- increasing citizens' confidence in the legal system.
In more detail, “Predictive Justice” is described by the Steering Research Team, coordinated by Prof. Giovanni Comandé, as “a multilayer project unfolding into five interconnected but autonomous levels”. The ambitions are multiple and transversal: from the attempt to “export” knowledge, techniques, and solutions across disciplines (e.g. from omics to legal data mining), to the coupling of protocols and software to automate the pseudonymisation of texts, or to the creation of innovative tools for querying legal materials through their automatic annotation, to the construction of predictive tools based on data science and Artificial Intelligence, to the attempt to offer comprehensible explanations on the functioning of the tools used and adapt them to the various end-users’ needs/abilities.
As Denise Amram clarifies: “In the start-up phase, the project aims to analyze decisions with the corresponding files of trial courts according to the criteria and methodologies developed in the Observatory on personal injury, applicable to areas of litigation other than non-pecuniary damages. Daniele Licari stresses “we are working on all-around justice innovation, working simultaneously on several aspects: automatic extraction of information from legal texts, anonymization, advanced search engines, and explainable predictive models. We support human decision-making by using technology to clearly draw the boundaries between interpretive consistency and unpredictable justice."
Il Sole 24 Ore has also published an article on automated legal decision-making approaches developed by the LIDER Lab of the Sant'Anna School in collaboration with EMbeDS, the KDD Lab, the Tribunale di Genova and, recently, the Tribunale di Pisa.
The Sole 24 Ore article and a downloadable pdf of the Automating Society Report 2020 (p. 150) are available on the right.