Confusion Matrix Calculator

Your details

Cases where the model correctly predicted the positive class.
Cases where the model predicted positive but the actual class was negative (Type I error).
Cases where the model predicted negative but the actual class was positive (Type II error).
Cases where the model correctly predicted the negative class.
AccuracyGood
0.88%

Fraction of all predictions that are correct: (TP + TN) / total

Precision (PPV)0.89%
Recall (Sensitivity / TPR)0.85%
Specificity (TNR)0.9%
F1 Score0.87%
Matthews Correlation Coefficient (MCC)0.7509
Balanced Accuracy0.88%
Negative Predictive Value (NPV)0.86%
False Positive Rate (FPR)0.1%
False Negative Rate (FNR)0.15%
False Discovery Rate (FDR)0.11%
Prevalence0.5%
Total Samples200
F2 Score0.86%
Accuracy0.88%
Precision0.89%
Recall0.85%
Specificity0.9%
F1 Score0.87%

Accuracy: 87.5% across 200 samples.

  • The model correctly classified 175 out of 200 samples (87.5% accuracy).
  • Precision (89.5%) and recall (85.0%) are well balanced.
  • The Matthews Correlation Coefficient is 0.751, indicating strong predictive agreement. MCC is the most balanced single-number summary for binary classifiers.

Next stepConsider tuning the decision threshold, resampling for class balance, or adjusting the cost of false positives vs false negatives to improve this result (F1 = 87.2%).

 = Powered by OnlyCalculators