Software Engineering Institute

As the Army moves quickly to seize on opportunities presented by big data, there is a natural tendency to focus on "the what and who" aspects of a solution. What technology do we need to design, purchase, and engineer? Who do we recruit, train, and develop to use this technology? Who leads this effort? However, much less attention has been devoted to how these personnel and technologies are specifically brought to bear on cyber operations. In this article, In this article, Maj. Gen. John W. Baker and Lt. Col. Steven J. Henderson, U.S. Army retired, outline the Cyber Data Science Process to address this question. The Cyber Data Science Process is a workflow of specific activities that define how data science should be incorporated with cyber operations. It combines the latest in data science research with doctrine and best practices found in military intelligence and targeting activities. We include a functional analysis of the workflow and identify the actions, skill sets, and products required at each stage.

This article was published in the Cyber Defense Review, Vol. 2, Issue 2, pp. 47-68.