PlanMine: Prediction plan failures using sequence mining. This paper presents the PlanMine sequence mining algorithm to extract patterns of events that predict failures in databases of plan executions. New techniques were needed because previous data mining algorithms were overwhelmed by the staggering number of very frequent, but entirely unpredictive patterns that exist in the plan database. This paper combines several techniques for pruning out unpredictive and redundant patterns which reduce the size of the returned rule set by more than three orders of magnitude. PlanMine has also been fully integrated into two real-world planning systems. We experimentally evaluate the rules discovered by PlanMine, and show that they are extremely useful for understanding and improving plans, as well as for building monitors that raise alarms before failures happen.
Keywords for this software
References in zbMATH (referenced in 9 articles , 1 standard article )
Showing results 1 to 9 of 9.
- Dutta, Kaushik; Vandermeer, Debra; Datta, Anindya; Keskinocak, Pinar; Ramamritham, Krithi: A fast method for discovering critical edge sequences in e-commerce catalogs (2007)
- Han, Jiawei; Cheng, Hong; Xin, Dong; Yan, Xifeng: Frequent pattern mining: Current status and future directions (2007)
- Sun, Xingzhi; Orlowska, Maria E.; Zhou, Xiaofang: Finding event-oriented patterns in long temporal sequences (2003)
- Chen, Yen-Liang; Chen, Shih-Sheng; Hsu, Ping-Yu: Mining hybrid sequential patterns and sequential rules (2002)
- Deshpande, Mukund; Karypis, George: Evaluation of techniques for classifying biological sequences (2002)
- Hilderman, Robert J.; Hamilton, Howard J.: Knowledge discovery and measures of interest (2001)
- Zaki, Mohammed J.: SPADE: An efficient algorithm for mining frequent sequences (2001)
- Zaki, Mohammed J.: Parallel sequence mining on shared-memory machines (2001)
- Zaki, Mohammed J.; Lesh, Neal; Ogihara, Mitsunori: PlanMine: Prediction plan failures using sequence mining (2000)