C4.5: programs for machine learning
C4.5: programs for machine learning
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
From data mining to knowledge discovery: an overview
Advances in knowledge discovery and data mining
On the Optimality of the Simple Bayesian Classifier under Zero-One Loss
Machine Learning - Special issue on learning with probabilistic representations
Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining
Global action rules in distributed knowledge systems
Fundamenta Informaticae
Action-Rules: How to Increase Profit of a Company
PKDD '00 Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery
Fast Algorithms for Mining Association Rules in Large Databases
VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases
Mining for Action-Rules in Large Decision Tables Classifying Customers
Proceedings of the IIS'2000 Symposium on Intelligent Information Systems
Mining Case Bases for Action Recommendation
ICDM '02 Proceedings of the 2002 IEEE International Conference on Data Mining
Action rules mining: Research Articles
International Journal of Intelligent Systems - Knowledge Discovery: Dedicated to Jan M. Żytkow
Mining for Interesting Action Rules
IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Mining Patterns That Respond to Actions
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Action Rules Discovery Based on Tree Classifiers and Meta-actions
ISMIS '09 Proceedings of the 18th International Symposium on Foundations of Intelligent Systems
Hi-index | 0.00 |
In this paper, we propose a novel algorithm which discovers a set of action rules for converting negative examples into positive examples. Unlike conventional action rule discovery methods, our method AARUDIA (Achievable Action RUle DIscovery Algorithm) considers the effects of actions and the achievability of the class change for disk-resident data. In AARUDIA, effects of actions are specified using domain rules and the achievability is inferred with Naive Bayes classifiers. AARUDIA takes a new breadth-first search method which manages actionable literals and stable literals, and exploits the achievability to reduce the number of discovered rules. Experimental results with inflated real-world data sets are promising and demonstrate the practicality of AARUDIA.