George is the chief architect of the Reach’s proprietary predictive software and technology. In long collaboration with top developer David S. Franklin, he designed it to encompass the know-how, algorithms and software for automated statistical modeling.
For over 30 years, George has been a leading data analysis innovator and designer in the computer-oriented school of Pattern Recognition. He was the first to fully develop kernel regression modeling, a technique with which he achieved accolades and awards in International Competition in Pattern Recognition. In the 1990’s his focus was on the simplification and automation of statistical modeling and scoring for direct marketing.
Previously, George was the first Senior Research Associate at Allstate’s Research and Planning Center. At the time he held the company’s highest technical title. George conceived and built an original approach to common stock selection for Allstate Insurance Company that led to a $400 million fund that for nine years bettered the S&P index by an average of 13 points.
In partnership with Mike Green, George initiated the design of simplified, automatic, high-speed modeling methods, and has been heavily engaged in its research and development ever since. In addition, over the last 20-plus years George has developed customer retention models for Pacific Bell and Chase Manhattan Bank, credit scoring for Sears, response modeling for United Group and Franklin Mint, and data analytic futures research for Transworld Oil and other traders.
George holds a BS in Physics from Iona College, but his career has exclusively been in data analysis methods and software. His published contributions include the vector field approach to clustering and the practical exploitation of information theory. His unpublished think piece for the layman, “The Bee Game” has received praise from a wide spectrum of readers.