Bounding XCS's parameters for unbalanced datasets

Authors:
Albert Orriols-Puig;Ester Bernadó-Mansilla
Affiliations:
Universitat Ramon Llull, Quatre Camins, Barcelona, Spain;Universitat Ramon Llull, Quatre Camins, Barcelona, Spain
Venue:
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Year:
2006

Citing 5
Cited 18

Accuracy-based learning classifier systems: models, analysis and applications to classification tasks

Evolutionary Computation
Analysis and improvement of fitness exploitation in XCS: bounding models, tournament selection, and bilateral accuracy

Evolutionary Computation
The class imbalance problem in learning classifier systems: a preliminary study

GECCO '05 Proceedings of the 7th annual workshop on Genetic and evolutionary computation
The class imbalance problem: A systematic study

Intelligent Data Analysis
Classifier fitness based on accuracy

Evolutionary Computation

Learning classifier systems: a complete introduction, review, and roadmap

Journal of Artificial Evolution and Applications
Substructrual surrogates for learning decomposable classification problems: implementation and first results

Proceedings of the 9th annual conference companion on Genetic and evolutionary computation
Modeling XCS in class imbalances: population size and parameter settings

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Towards increasing learning speed and robustness of XCSF: experimenting with larger offspring set sizes

Proceedings of the 10th annual conference companion on Genetic and evolutionary computation
Coevolutionary bid-based genetic programming for problem decomposition in classification

Genetic Programming and Evolvable Machines
Agent Learning Instead of Behavior Implementation for Simulations --- A Case Study Using Classifier Systems

MATES '08 Proceedings of the 6th German conference on Multiagent System Technologies
Learning Classifier Systems: Looking Back and Glimpsing Ahead

Learning Classifier Systems
Evolving Fuzzy Rules with UCS: Preliminary Results

Learning Classifier Systems
Revisiting UCS: Description, Fitness Sharing, and Comparison with XCS

Learning Classifier Systems
Intrusion detection with evolutionary learning classifier systems

Natural Computing: an international journal
Learning sensorimotor control structures with XCSF: redundancy exploitation and dynamic control

Proceedings of the 11th Annual conference on Genetic and evolutionary computation
On the scalability of XCS(F)

Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Evolutionary undersampling for classification with imbalanced datasets: Proposals and taxonomy

Evolutionary Computation
Learning classifier systems: a complete introduction, review, and roadmap

Journal of Artificial Evolution and Applications
Facetwise analysis of XCS for problems with class imbalances

IEEE Transactions on Evolutionary Computation
Controlling a four degree of freedom arm in 3D using the XCSF learning classifier system

KI'09 Proceedings of the 32nd annual German conference on Advances in artificial intelligence
How XCS deals with rarities in domains with continuous attributes

Proceedings of the 12th annual conference on Genetic and evolutionary computation
A combined approach to tackle imbalanced data sets

International Journal of Hybrid Intelligent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper analyzes the behavior of the XCS classifier system on imbalanced datasets. We show that XCS with standard parameter settings is quite robust to considerable class imbalances. For high class imbalances, XCS suffers from biases toward the majority class. We analyze XCS's behavior under such extreme imbalances and prove that appropriate parameter tuning improves significantly XCS's performance. Specifically, we counterbalance the imbalance ratio by equalizing the reproduction probabilities of the most occurring and least occurring niches. The study provides guidelines to tune XCS's parameters for unbalanced datasets, based on the dataset imbalance ratio. We propose a method to estimate the imbalance ratio during XCS's training and adapt XCS's parameters online.