The Exploit Prediction Scoring System, or EPSS, is a daily score from FIRST that estimates the probability that a vulnerability will see exploitation activity in the next 30 days. The score is a number between 0 and 1, often shown as a percentage, and it is calculated from data about the vulnerability and observed activity.
EPSS answers a different question from CVSS. CVSS describes how severe a flaw could be, while EPSS estimates how likely exploitation is. Used together, they can help teams decide which of many vulnerabilities to fix first, because a severe flaw that is unlikely to be exploited may rank below a moderate one that attackers are actively using.
A score is a probability, not a verdict. A low score does not mean a flaw is safe, and a high score does not mean your systems are being attacked. Scores change daily, and new vulnerabilities may not have much data behind them yet. Confirmed exploitation, such as listing in CISA's Known Exploited Vulnerabilities catalog, is stronger evidence than a prediction.
To use it, combine EPSS with KEV status, CVSS and your own exposure, such as whether the affected system is internet-facing and holds sensitive data. Re-check scores regularly and record why each patching decision was made.