Rule-based Classifier Models
Cecilia Di Florio, Huimin Dong, Antonino Rotolo
TL;DR
The paper addresses the limitation of predictive justice models that rely solely on case facts by introducing a rule-based extension to classifier models that incorporates the ratio decidendi through sets of admissible rules. It defines a Rule-based Classifier Model (RCM) where each state comprises a factual subset and an applicable rule solution, and links these states to case bases, enabling rule-driven and precedent-informed decisions. A central contribution is the formalization of a relevance relation that encodes precedential constraints and governs how past cases constrain new decisions, along with mechanisms to ensure minimal, compatible rule sets. The work also discusses incorporating hierarchical court structures and temporal ordering (as in PrecedentsClash) to resolve conflicts among binding precedents, paving the way for more transparent and justifyable predictive justice systems.
Abstract
We extend the formal framework of classifier models used in the legal domain. While the existing classifier framework characterises cases solely through the facts involved, legal reasoning fundamentally relies on both facts and rules, particularly the ratio decidendi. This paper presents an initial approach to incorporating sets of rules within a classifier. Our work is built on the work of Canavotto et al. (2023), which has developed the rule-based reason model of precedential constraint within a hierarchy of factors. We demonstrate how decisions for new cases can be inferred using this enriched rule-based classifier framework. Additionally, we provide an example of how the time element and the hierarchy of courts can be used in the new classifier framework.