Evolution of symposia on the interface of computing and statistics defines data science to be the interface

摘要

Goal of this article is to document evolution of the Interface and its Symposia, from their conception and birth when small data were analyzed with Statistics in the mid 20th Century until Big Data are now analyzed with Data Science in the early 21st Century.Wilfrid Dixon's 1961 BMD Statistical Program Package was a pioneer predictor of Computing in Statistics, and Arthur Samuel's 1965 presentation on using game-branch probabilities in teaching ILLIAC I to play checkers was a pioneer predictor of Statistics in Computing. Such predictors produced a perception that future interactions of Computing and Statistics might constitute a significant and productive Interface of Computing and Statistics. Another perception included Computing and Statistics with Computing in Statistics and Statistics in Computing. This presented the challenge of organizing an Interface Symposium, to introduce the Interface to a vibrant environment for Computing and Statistics in Southern California. Presentations at the Symposia reveal that small data are in the process of becoming Big Data, while Computing in Statistics and Machine Learning are becoming the Interface, and the Interface is becoming Data Science. Data Science, the first comprehensive Journal on Data Science, another 1 of the 15 ASA Journals as well as 3 of 21 ASA Sections constitute a proud heritage for Interface and its Symposia. Perspective of the article is shaped by 60 years of pioneering and continuously contributing to the Interface and its Symposia, which few can match.