Applying Data-Driven Methodologies to Generate More Meaningful Cybersecurity Ratings
SecurityScorecard rates more than two million companies across a range of sizes, industrial sectors, and geographical locations. Our analysis of a growing collection of cybersecurity data allows us to quickly understand and continuously monitor the cyber health of organizations, and provide SecurityScorecard users with valuable and unique insights.
In order to make our Security Ratings as meaningful as possible, we conducted a study in which we applied machine learning (ML) to ensure that our letter grades are maximally correlated with the relative risk of sustaining a data breach. This allows organizations to make more informed, risk-based business decisions based on the most accurate data available.
After applying machine learning-tuned factor weights to our sample data, we found that organizations with an F rating are 7.7x more likely to sustain a breach than those with an A.