A Comparison of ILP and Propositional Systems
on Propositional Traffic Data

Sam Roberts1 , Wim vanLaer2, Nico Jacobs2, Stephen Muggleton3, and
Jeremy Broughton4

1 Oxford University Computing Laboratory
Samuel.Roberts@comlab.ox.ac.uk
2 Department of Computer Science, Katholieke Universiteit Leuven
{Wim.VanLaer, Nico.Jacobs}@cs.kuleuven.ac.be
3 Department of Computer Science, University of York
stephen@cs.york.ac.uk
4 Transport Research Laboratory, Crowthorne, Berkshire
JeremyB@E.TRL.CO.UK


Abstract. This paper presents an experimental comparison of two Inductive 
Logic Programming algorithms, PROGOL and TILDE, with C4.5,
a propositional learning algorithm, on a propositional dataset of road
traffic accidents. Rebalancing methods are described for handling the
skewed distribution of positive and negative examples in this dataset ,
and the relative cost of errors of commission and omission in this domain. 
It is noted that before the use of these methods all algorithms
perform worse than majority class. On rebalancing, all did significantly
better. The conclusion drawn from the experimental results is that on
such a propositional dataset ILP algorithms perform competitively in
terms of predictive accuracy with propositional systems, but are significantly 
outperformed in terms of time taken for learning.
References

[1]	R. Agrawal, H. Mannila, R. Srikant, H. Toivonen, and A.I. Verkamo. Fast discovery 
of association rules. In Advances in Knowledge Discovery and Data Mining,
pages 307328. MIT Press, 1996.
[2]	H. Blockeel and L. De Raedt. Lookahead and discretization in ILP. In Proceedings
of the 7th International Workshop on Inductive Logic Programming, volume 1297
of Lecture Notes in Artificial Intelligence, pages 7785. Springer-Verlag, 1997.
[3]	H. Blockeel and L. De Raedt. Top-down induction of first order logical decision
trees. Submitted, 1998.
[4] P. Clark and R. Boswell. Rule induction with CN2: Some recent improvements.
In Yves Kodratoff, editor, Proceedings of the 5th European Working Session on
Learning, volume 482 of Lecture Notes in Artificial Intelligence, pages 151163.
Springer-Verlag, 1991.
[5]	P. Clark and T. Niblett. The CN2 algorithm. Machine Learning, 3(4):261284,
1989.
[6] J. Cussens, D. Page, S. Muggleton, and A. Srinivasan. Using Inductive Logic
Programming for Natural Logic Processing. In W. Daelemans, T. Weijters, and
A.	van der Bosch, editors, ECML 97  Workshop Notes on Empirical Learning
of Natural Language Tasks, pages 2534, Prague, 1997. University of Economics.
Invited keynote paper.
[7]	L. Dehaspe and L. De Raedt. Mining association rules in multiple relations. In
Proceedings of the 7th International Workshop on Inductive Logic Programming,
volume 1297 of Lecture Notes in Artificial Intelligence, pages 125132. Springer-
Verlag, 1997.
[8]	B. Dolsak and S. Muggleton. The application of Inductive Logic Programming to
finite element mesh design. In S. Muggleton, editor, Inductive Logic Programming,
pages 453472. Academic Press, London, 1992.
[9]	R.S. Michalski. A theory and methodology of inductive learning. In Machine
Learning: an artificial intelligence approach, volume 1. Morgan Kaufmann, 1983.
[10]	S. Muggleton. Inductive logic programming. New Generation Computing,
8(4):295318, 1991.
[11]	S. Muggleton. Inverse entailment and Progol. New Generation Computing,
13:245286, 1995.
[12] J.R. Quinlan. Induction of decision trees. Machine Learning, 1(1):81106, 1986.
[13] J.R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, 1993.
Morgan Kaufmann series in machine learning.
[14]	L. De Raedt. Induction in logic. In R.S. Michalski and J. Wnek, editors, Proceedings 
of the 3rd International Workshop on Multistrategy Learning, pages 2938,
1996.
[15]	L. De Raedt and S. Dzeroski. First order jk-clausal theories are PAC-learnable.
Artificial Intelligence, 70:375392, 1994.
[16]	A. Srinivasan, S. Muggleton, R. King, and M. Sternberg. Theories for mutagenicity: 
a study of first-order and feature based induction. Artificial Intelligence,
85(1,2):277299, 1996.
[17]	B. Williams, S. Roberts, and S. Muggleton. Use of ILP to investigate accident
data: final report. Technical Report JA022D010-0.1, Smith System Engineering,
Surrey Research Park, Guildford, Surrey GU2 5YP, September 1997.
