ID  - jf:TUD-KE-2007-02
T1  - Meta-Learning Rule Learning Heuristics
A1  - Janssen, Frederik
A1  - F├╝rnkranz, Johannes
Y1  - 2007
IS  - TUD-KE-2007-02
T2  - TU Darmstadt, Knowledge Engineering Group
UR  - http://www.ke.informatik.tu-darmstadt.de/publications/reports/tud-ke-2007-02.pdf
N2  - The goal of this paper is to investigate to what extent a rule learning heuristic can
be learned from experience. Our basic approach is to learn a large number of rules and
record their performance on the test set. Subsequently, we train regression algorithms on
predicting the test set performance from training set characteristics. We investigate several
variations of this basic scenario, including the question whether it is better to predict
the performance of the candidate rule itself of the resulting final rule. Our experiments
on a number of independent evaluation sets show that the learned heuristics outperform
standard rule learning heuristics. We also analyze their behavior in coverage space.
ER  -