Mining Needles in a Haystack: Classifying Rare Classes via Two-Phase Rule Induction

Summary: Two-phase rule induction for rare-class learning: Phase I aims for high recall with broad-support rules; Phase II prunes false positives to improve precision. Synthetic models show when RIPPER and C4.5rules falter; on real intrusion data, the method yields balanced recall–precision comparable or superior. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 3322
Venue: SIGMOD
Year: 2001
Pagerank: -
Overall Rank: 14,068 | 3.82%
DOI: 10.1145/375663.375673

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Mahesh V. Joshi (IBM; University of Minnesota)
2. Ramesh C. Agarwal (IBM)
3. Vipin Kumar (University of Minnesota)

BibTeX Citation

@inproceedings{joshi_sigmod01,
        title = {{Mining Needles in a Haystack: Classifying Rare Classes via Two-Phase Rule Induction}},
        author = {Joshi, Mahesh V. and Agarwal, Ramesh C. and Kumar, Vipin},
        series = {{SIGMOD} '01},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/375663.375673},
        url = {https://dl.acm.org/doi/10.1145/375663.375673},
        year = {2001}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	2,159	Nearest Neighbor Classifiers over Incomplete Information: From Certain Answers to Certain Predictions	2021	VLDB
2	6,719	Ratio Rules: A New Paradigm for Fast, Quantifiable Data Mining	1998	VLDB
3	4,222	Outlier Detection for High Dimensional Data	2001	SIGMOD
4	5,378	Towards Proximity Pattern Mining in Large Graphs	2010	SIGMOD
5	1,222	Maintaining Data Privacy in Association Rule Mining	2002	VLDB
6	11,212	Similarity Joins of Sparse Features	2024	SIGMOD
7	5,569	Mining Frequent Patterns with Differential Privacy	2013	VLDB
8	8,207	Efficient Discovery of Sequence Outlier Patterns	2019	VLDB
9	10,040	Discovering Top-k Relevant and Diversified Rules	2024	SIGMOD
10	7,797	Outlier Summarization via Human Interpretable Rules	2024	VLDB