Computer Engineering Department, Cairo University
Ph.D. California Institute of Technology
Was born in Cairo, Egypt. He received his B.S.
degree in 1982 from Cairo University (Egypt), and the M.S. and
Ph.D. degrees in 1986 and 1991 from Caltech, Pasadena, CA,
all in electrical engineering. He held positions in academia,
as well as several positions in financial firms.
From 1997 to 2001 he was a Visiting Associate at Caltech.
On leave from Cairo University, he recently held research positions in the firms
Simplex Risk Management,
Hong Kong, Countrywide Corporation in Los Angeles,
and Dunn Capital Management, Florida.
Currently, he is a Research Scientist with Veros Systems, Texas.
He has been active in research in several fields. He received
the Egyptian State Prize for Best Research in Science and
Engineering, in 1994, and the Egyptian State Distinction Award, in 2011. He also received the Young Investigator
Award from the
International Neural Network Society
in 1996. In 2005 he received the prestigeous Kuwait Prize
by the Kuwait Foundation for the Advancement of Sciences.
Currently, he is an associate editor for
International Journal of Forecasting.
He was an Associate Editor for
IEEE Transactions Neural Networks,
from 1998 to 2008.
He was guest editor of the special issue (July 2001) of
IEEE Transactions Neural Networks on
Neural Networks in Financial Engineering.,
and was guest editor of the special issue (September 2005) of IEEE Transactions Neural Networks on
Adaptive Learning Systems in Communications Networks.
Business and telecom applications of data mining.
Time Series Forecasting.
Trading system design.
Monte Carlo methods.
Application of stochastic methods and optimization theory to communications networks.
Some Recent Work:
Dynamic pricing is the theory of adjusting the price of a merchandise dynamically
with time in an attempt to maximize revenue. It started in the airline industry,
and has grown substantially to cover many types of products.
We have developed a number of dynamic pricing models,
applied to the hotel industry
and to the telecom industry.
Our models rely on large scale Monte Carlo or agent based
simulation. They have aspects of learning
process parameters, time series forecasting,
and emulating buyer's behavior, all combined
in a way to achieve an accurate and realistic
modeling of demand, and subsequently obtaining
the optimal pricing strategy.
(see hotel modeling,
and hotel dynamic pricing papers).
Analyzing the Maximum Drawdown:
Theoretical analysis of the maximum drawdown risk measure, developing formulas
relating it with the Sharpe Ratio, and analyzing its asymptotic behavior.
See the papers maximum drawdown 1 (Journal
of Applied Probability)
and maximum drawdown 2 (Risk Magazine).
The developed theoretical formula (for the expected maximum drawdown)
was selected by Matlab and included in
the financial time series toolbox of
Also, it was selected to be included in Wikipedia, the on-line encyclopedia:
drawdown on wikipedia)
A Large Scale Comparison of Machine Learning and Forecasting Models:
A large scale and thorough study for 8 major machine learnine models for time series forecasting
involving around 1000 time series from the M3 benchmark data.
See the paper comparison 1
(appeared in the Econometric Reviews journal).
Based on this study, we participated in the
NN5 Forecasting Competition for Artificial Neural Networks & Computational Intelligence
, which is a major international competition.
Our rank was first out of 19 in one time series category and 3 out of 29
in other category. See
, (the team Andrawis/Atiya/El-Shishiny)
where there is a table of competition rankings
In another precursor competition, the
NN3 Artificial Neural Networks & Computational Intelligence Forecasting Competition
our rank was 5th (out of 44) and 6th (out of 26) in respectively the two categories.
These competitions were sponsored by SAS Inc., and International Institute of Forecasters, and their results
appeared in a special issue of
International Journal of Forecasting.,