US Patent 11748685 Utilizing machine learning to measure application developers' cybersecurity competencies

An automated method for improving application developers' cybersecurity competencies is provided. The method includes: breaking each application of a set of computer applications into one or more pieces each piece being developed by a corresponding one of a plurality of application developers; associating each piece of each application with its corresponding application developer; performing cybersecurity assessment testing on the set of computer applications in order to generate cybersecurity assessment results for the set of computer applications; building a cybersecurity competency profile for each application developer using the generated cybersecurity assessment results attributed to corresponding pieces associated with the application developer; grouping the application developers into at least two groups using unsupervised machine learning on the built cybersecurity competency profiles; and choosing, for each application developer based on the corresponding groups to which the application developer belongs, a subset of training courses to improve the cybersecurity competency of the application developer.