3 Law, Prob. & Risk 147 (2004)
The Split-up Project: Induction, Context and Knowledge Discovery in Law

handle is hein.journals/lawprisk3 and id is 153 raw text is: Law, Probability and Risk (2004) 3, 147-168

The Split-up project: induction, context and knowledge discovery in
law
JOHN ZELEZNIKOWt
Joseph Bell Centre for Forensic Statistics and Legal Reasoning, Faculty of Law, University of
Edinburgh, Old College, South Bridge, Edinburgh EH8 9YL, UK
[Received on 28 March 2003; revised on 25 January 2004; accepted on 2 February 2004]
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.
Keywords: induction; knowledge; discovery; discretion; legal decision; support systems.
1. Introduction
The Split-Up project aims to examine how to model the exercise of discretion in legal decision-
making. In doing so, the author and others have developed jurisprudential theories which suggest
we may wish to apply knowledge discovery from database (KDD) processes to law.
According to Fayyad et al. (1996) knowledge discovery from databases is the 'non trivial
extraction of implicit, previously unknown and potentially useful information from data'.
Knowledge discovery techniques have not been applied extensively in the legal domain despite
potential benefits in the automated generation of legal knowledge from data. The absence of data in
quantities collected in other fields such as astronomy accounts, in part, for this trend. However, for
the most part, KDD has not been extensively performed with legal data because of a lack of clarity
about how this can be achieved.
Theories of jurisprudence have proved indispensable for the analysis and development of
computational models of legal reasoning. For example, the rule positivism of Hart (1961) underpins
the application of logic programming in law exemplified by Sergot et al. (1986). The identification
of jurisprudential theories that are particularly applicable to improve KDD in law, and how they can
be applied, is the primary objective of this research project.
KDD techniques in general can be grouped into four categories:
t E-mail: john.zeleznikow@ed.ac.uk

g) Oxford University Press 2004, all rights reserved

What Is HeinOnline?

HeinOnline is a subscription-based resource containing nearly 2,700 academic and legal journals from inception; complete coverage of government documents such as U.S. Statutes at Large, U.S. Code, Federal Register, Code of Federal Regulations, U.S. Reports, and much more. Documents are image-based, fully searchable PDFs with the authority of print combined with the accessibility of a user-friendly and powerful database. For more information, request a quote or trial for your organization below.



Short-term subscription options include 24 hours, 48 hours, or 1 week to HeinOnline with pricing starting as low as $29.95

Access to this content requires a subscription. Please visit the following page to request a quote or trial:

Already a HeinOnline Subscriber?