Upload a CSV with a true yes/no outcome and a model score, and get the full ROC curve, AUC with a confidence interval, and the optimal decision cutoff — sensitivity, specificity, and all. Free.
Free analyses run on up to 10,000 rows. Larger files are randomly sampled to that size — sign up to analyze your full dataset.
Drawing the ROC curve and computing AUC...
Sent to — ROC curve, AUC with a 95% confidence interval, the Youden-optimal cutoff with sensitivity and specificity, a threshold sweep, R code, and AI insights.
Analyze another fileThe analysis treats one class as positive, then sweeps every candidate cutoff on your score to trace the ROC curve — true positive rate against false positive rate. The area under that curve (AUC) is the probability a random positive scores higher than a random negative; it is reported with a Hanley-McNeil 95% confidence interval and cross-checked against the curve's own trapezoidal area. Youden's J picks the cutoff that maximizes sensitivity plus specificity, and the report gives sensitivity, specificity, PPV, NPV, accuracy, and the confusion counts at that cutoff.
Use it when you have a real yes/no outcome and a continuous score or probability, and you want to know both how good the score is and where to set the decision threshold.
Not for multi-class outcomes and not a substitute for calibration analysis — AUC judges ranking, not whether predicted probabilities are numerically right.
Built for: Analysts, data scientists, and operators evaluating a classifier or diagnostic score
Typical data source: A table with a true binary label and a model score or probability per row
Any table with a true yes/no outcome and a numeric score. For example, a churn model's scored customers:
Minimum 20 rows · Best with 200-50,000 rows with at least 10 of each class
Standard-library analysis: evaluate a binary classifier or diagnostic score against the true yes/no outcome. Draws the full ROC curve, computes the AUC with a 95% confidence interval, and finds the best operating cutoff by Youden's J — with sensitivity, specificity, PPV, NPV, accuracy, and the confusion counts at that cutoff. Works on any dataset: map the true outcome and a numeric score where higher means more likely positive.
The ROC curve — the higher it bows toward the top-left corner, the better the score separates the two classes; the diagonal is pure chance.
AUC, its confidence interval, and every operating-point metric at the recommended Youden cutoff, so you know exactly what that decision threshold buys.
Sensitivity and specificity at candidate cutoffs, so you can see the trade-off and move the line to suit your costs.
Plain-English interpretation — what the numbers mean, what's significant, and what to do next.
How good is my classifier, and where should I set the cutoff?
Map your true yes/no outcome and the model's score. The ROC curve and AUC tell you how well the score ranks positives above negatives, and the Youden-optimal cutoff tells you exactly where to draw the line — with the sensitivity and specificity you get there.
See our FAQ for details on pricing, data privacy, and how the analysis works. Every report includes a Methodology section showing the statistical test, assumptions checked, and diagnostics run.
Run any analysis on your own data — validated R analyses, interactive reports, AI insights, and PDF export.
Try Free — No Credit CardTell us what went wrong, in your own words. We capture the page you're on automatically, so no need to describe where you are.