Sanjay Chawla

PhD (University of Tennessee)
Professor

Contact Information

Office: School of IT, J12. Room 4W-424.
Phone: +61 2 9351 3516
Email: sanjay.chawla AT sydney.edu.au

Research Interests

My interests straddle data mining, machine learning and spatial data management. I also enjoy discussing philosophical issues related to data mining. My current emphasis is on problems such as :

  • Anomaly detection in high dimensional space.
  • Classification for imbalanced data.
  • Learning in adversarial environments.

Best Paper Awards

  • On Mining Anomalous Patterns in Road Traffic Streams. ADMA (2) 2011:237 -251
  • Finding Local Anomalies in Very High Dimensional Space. IEEE ICDM 2010:128-137
  • Spatio-temporal Outlier Detection in Precipitation Data. KDD Workshop on Knowledge Discovery from Sensor Data 2008:115-133
  • Mining for Outliers in Sequential Databases. SIAM International Conference on Data Mining, 2006.

Recent Publications

  • Timothy de Vries, Hui Ke, Sanjay Chawla and Peter Christen: Robust Record Linkage Blocking using Suffix Arrays and Bloom Filters. ACM Transactions on Knowledge Discovery from Data (TKDD). Volume 5, Number 2, February 2011. DOI 10.1145/1921632.1921635 [PDF] [BibTeX]
  • Timothy de Vries, Sanjay Chawla and Michael Houle: Density-preserving Projections for Large-scale Local Anomaly Detection. Knowledge and Information Systems. DOI 10.1007/s10115-011-0430-4 [PDF]
  • Timothy de Vries, Sanjay Chawla and Michael Houle: Finding Local Anomalies in Very High Dimensional Space. In Proceedings of the 10th IEEE International Conference on Data Mining (ICDM), Sydney, December 2010. (ERA Rank A, Best Paper Award) [PDF]
  • Wei Liu and Sanjay Chawla: Mining Adversarial Patterns via Regularized Loss Minimization. Machine Learning (Special issue for ECML PKDD 2010). Volume 81, Issue 1, Pages 69-83. (ERA Rank A*, Top Seven Papers at ECML) [PDF]

For a complete list, see my publications page.