Gary Weiss

Dr. Gary Weiss is an associate professor of computer and information science at Fordham University. Prior to this, he worked at Bell Labs and then AT&T Labs. Dr. Weiss started his career at AT&T as a software engineer, before moving on to expert system development, and, finally, data mining. Dr. Weiss spent his final five years at AT&T in a marketing analysis group, using data mining methods to solve complex business problems.

Dr. Weiss completed his undergraduate education at Cornell University, where he received his B.S. degree in computer science. He earned his M.S. in computer science from Stanford University and his Ph.D. degree in computer science from Rutgers University. Dr. Weiss has published numerous papers in the areas of machine learning, data mining, expert systems, and object-oriented programming. He is considered an expert in the use of data mining in the telecommunications domain.

My primary research area is machine learning/data mining. Machine learning strives to automatically improve the performance of a system over time, as experience is accumulated, whereas the related area of data mining is interested in extracting useful knowledge from large amounts of data. In general, I am interested in studying how we can deal with many of the real-world issues that make learning, and data mining, more difficult. My recent work has focused on how class distribution affects data mining and how one might be able to choose data intelligently when data is costly, to improve the effectiveness of data mining. I have also studied the problem of why it is so difficult to deal with rare cases and rare classes in data mining.

I have also conducted research in a few other areas, during my time in industry. This includes research in expert systems and in object technology.

Gary. M. Weiss and Ye Tian (2008). "Maximizing Classifier Utility when there are Data Acquisition and Modeling Costs", Data Mining and Knowledge Discovery,

Gary. M. Weiss, Kate McCarthy, and Bibi Zabar (2007). " Cost-Sensitive learning vs. Sampling: Which is Best for Handling Unbalanced Classes with Unequal Error Costs?", Proceedings of the 2007 International Conference on Data Mining (DMIN-07). CSREA Press, Las Vegas, NV, June 2007.

Gary. M. Weiss (2006). "Maximizing Classifier Utility When Training Data is Costly", SIGKDD Explorations, 8(2)

Gary. M. Weiss (2006). "UBDM 2006: Utility-based Data Mining Workshop Report", SIGKDD Explorations, 8(2)

Gary. M. Weiss (2006). "Proceedings of the Second ACM International Workshop on Utility-Based Data Mining (editors)", ACM Press, Philadelphia, PA, August 2006.

Gary. M. Weiss, Maytal Saar-Tsechansky, and Bianca Zadrozny (2005). Proceedings of the First International Workshop on Utility-Based Data Mining (editors). ACM Press, Chicago, IL, August 2005.

Gary. M. Weiss (2005). " Mining Rare Cases". In O. Maimon and L. Rokach (.eds), Data Mining and Knowledge Discovery Handbook: A Complete Guide for Practitioners and Researchers. Kluwer Academic Publishers, 765-776.

Gary. M. Weiss (2005). " Data Mining in Telecommunications". In O. Maimon and L. Rokach (.eds), Data Mining and Knowledge Discovery Handbook: A Complete Guide for Practitioners and Researchers. Kluwer Academic Publishers, 1189-1201.

Gary. M. Weiss (2004). "Mining with Rarity: A Unifying Framework", SIGKDD Explorations, 6(1):7-19

Gary. M. Weiss and Foster Provost (2003). "Learning when Training Data are Costly: The Effect of Class Distribution on Tree Induction", Journal of Artificial Intelligence Research, 19:315-354