Work

Accuracy Is Not Enough: Confusion Matrix Metrics That Actually Work in CVE Impact Prediction

Year: 2025

Type: article

Abstract: In high-stakes environments like healthcare, autonomy, critical infrastructure, finance, and security - false negatives carry outsized consequences. One miss can overwhelm every other metric, which is why recall, calibrated thresholds, and decision SLAs matter more than plain accuracy. By reframing the confusion matrix into levels (L0-L6), I show how to work backwards from risk exposure and design metrics that guide both model calibration and system-level SLAs. In finance and cyber, predictive models aren’t judged by elegance, but by how deterministically they can protect capital, data, and trust. The right metrics are the difference between models that look good on paper vs. systems that deliver measurable ROI.

DOI: 10.5281/zenodo.17438182

Author: Purushotham, Keerthana

Institutions: Amazon (United States), Institute of Electrical and Electronics Engineers, University of California San Diego, Linux Foundation, Ramaiah Institute of Technology

Language: English

Topic: Information and Cyber Security

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

OpenAlex ID: W7094956001

FWCI:

Cites:

Cited by:

Related to: