|
Saharon Rosset has received his B.S. in Mathematics and M.Sc, in Statistics from Tel Aviv University in Israel, and his Ph.D. in Statistics from Stanford University in 2003. His Ph.D. thesis is titled "Topics in Regularization and Boosting" and is concentrated around the importance of regularization --- that is, controlling the complexity of prediction models --- in modern data analysis, machine learning and data mining.
Saharon worked as a data mining researcher at Amdocs Ltd. from 1997 to 1999 and as a data mining consultant between 1999 and 2003. His industrial data mining projects were in applications in the telecommunications industry: churn analysis, fraud analysis, lifetime value modeling and more. Saharon headed the group which won the yearly data mining competition in 1999 (KDD-Cup 99) and consulted the group which won two of the five sub-competitions in KDD-Cup 00. He is the primary author of the paper "Lifetime Value Modeling and its Use for Customer Retention Planning", which has won the Best Application Paper award at the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2002).
Saharon joined the Data Analytics Group at IBM Research in September 2003. His research interests at IBM are in applying complex modeling approaches to practical problems.
|
