Applied Probability, Financial Engineering, Network Design and Analysis, Statistics

Office: 220 Rhodes

Phone: 607.255.9141

Website: click here

Fax: 607.255.9129

Gennady Samorodnitsky received his B.S. in 1978 from the Moscow Steel and Alloys Institute, USSR, his M.S. and his D. Sc. 1986 from Technion, Israel in 1983. He joined the School of Operations Research and Industrial Engineering in 1988. After completing his doctorate, Samorodnitsky spent two years as a visiting professor, first at the University of North Carolina at Chapel Hill and then at Boston University.

His research interests lie both in probability theory and in its various applications. A very important area is that of stochastic modeling, and he is especially interested in "non-standard" models, in particular those exhibiting heavy tails and/or long-range dependence. These models behave very differently from the "usual" models that are typically based on Gaussian or Markov stochastic processes. Both heavy tails and long-range dependence are observed in financial processes, teletraffic processes and many other processes. Since many classical statistical tools break down in the presence of long-range dependence and/or absence of Gaussianity, it is very important to understand how "non-standard" models behave, how one simulates them, how one estimates their parameters, and how one predicts their behavior in the future. He is looking closely, in particular, at certain financial and queueing models. Other areas of interest include stochastic processes in semiconductor manufacturing, self-similar (fractal-like) stochastic processes, extrema of stochastic processes, zero-one laws, positive and negative dependence in stochastic processes, stable and other infinitely divisible processes and level crossings of stochastic processes.

Select Publications

“Extreme value theory, ergodic theory, and the boundary between short memory and long memory for stationary stable processes”. Annals of Probability 32, 1438 -1468 (2004).

"Long strange segments of a stochastic process and long range dependence”. Annals of Applied Probability 11, 878 - 921 (2001). (With P. Mansfield and S. Rachev)

"Multivariate extremes, aggregation and risk estimation”. Quantitative Finance 1 (1), 79 - 95 (2001). (With H. Hauksson, M. Dacorogna, T. Domenig, and U. Muller)

"How system performance is affected by the interplay of averages in a fluid queue with long range dependence induced by heavy tails”. Annals of Applied Probability 9, 352 - 375 (1999). (With D. Heath and S. Resnick)

Lectures

The Third International Symposium on Extreme Value Analysis. Keynote talk, "Extremes of stationary stable processes''. Aveiro, Portugal, July 19-23 (2004).

2e Colloque Autosimilarite & Applications. Plenary talk, "Long memory and self-similar processes''. Toulouse, June 20-24 (2005).

4th Conference on Extreme Value Analysis: Probabilistic and Statistical Models and their Applications. "Poisson cluster process as a model for teletraffic arrivals and its extremes''. Gothenburg, Sweden, August 15-19 (2005).

Deutsche Bundesbank Conference on Heavy Tails and Stable Paretian Distributions in Finance and Macroeconomics. "Asymptotic distribution of unbiased linear estimators in the presence of heavy-tailed stochastic regressors and residuals''. Eltville, Germany, November 10-12 (2005).

Professional Activities

Member of the Institute of Mathematical Statistics and Bernoulli Society

Associate Editor, Probability and Mathematical Statistics, Stochastic Models, Stochastic Processes and Their Applications

Advisory Editor, Frontiers in Mathematics, Series of Birkhauser

University Activities

Director of Graduate Studies for Operations Research

Awards and Recognition

Wolf Foundation scholarship

Chaim Weizmann Foundation postdoctoral fellowship

Fellow Institute of Mathematical Statistics