Performance of a cognitive personal assistant, RADAR, consisting of multiple machine learning components, natural language processing, and optimization was examined with a test explicitly developed to measure the impact of integrated machine learning when used by a human user in a real world setting. Three conditions (conventional tools, Radar without learning, and Radar with learning) were evaluated in a large-scale, between-subjects study. The study revealed that integrated machine learning does produce a positive impact on overall performance. This paper also discusses how specific machine learning components contributed to human-system performance.

: The RADAR (Reflective Agents with Distributed Adaptive Reasoning) project involves a collection of machine learning research thrusts that are integrated into a cognitive personal assistant. Progress is examined with a test developed to measure the impact of learning when used by a human user. Three conditions (conventional tools, Radar without learning, and Radar with learning) are evaluated in a large-scale, between-subjects study. This paper describes the RADAR Test with a focus on test design, test harness development, experiment execution, and analysis. Results for the 1.1 version of Radar illustrate the measurement and diagnostic capability of the test. General lessons on such efforts are also discussed.