The Split-up project: induction, context and knowledge discovery in law

Abstract

Most legal decision support systems have generally operated in domains with well-understood norms. Hence reasoning has been represented by a combination of rule-based and case-based reasoning. However, we analyse legal domains in which decision makers are allowed a significant amount of discretion. We argue that if the domain is bounded, and a sufficient number of commonplace cases exist, then the domain can be modelled using Knowledge Discovery from Databases techniques. Whilst we focus upon legal principles for decision making in discretionary legal domains, our goal is to develop theory for constructing legal decision support systems. Our jurisprudential theory is hence applied to a practical legal domain-namely the distribution of marital property following divorce in Australia. We conclude by discussing how we can maintain, update and evaluate the quality of the advice offered by our legal decision support systems.