Matthews Correlation Coefficient Calculator

TATITIC CALCULATOR Matthews Correlation Coefficient A precise tool.
📖
What is the Matthews Correlation Coefficient & How does it work?

The Matthews Correlation Coefficient (MCC) is a balanced measure that can be used even if the classes are of very different sizes. It returns a value between –1 and +1 where +1 indicates a perfect prediction, 0 no better than random, and –1 an inverse prediction.

MCC takes into account all four quadrants of the confusion matrix: true positives (TP), true negatives (TN), false positives (FP) and false negatives (FN). This makes it especially useful for binary classification problems with imbalanced datasets.

Because MCC is a correlation coefficient, it is symmetric with respect to the two classes and can be interpreted similarly to Pearson’s r, providing an intuitive sense of the classifier’s performance.

MCC = \frac{TP\cdot TN – FP\cdot FN}{\sqrt{(TP+FP)(TP+FN)(TN+FP)(TN+FN)}}
TP = true positives, TN = true negatives, FP = false positives, FN = false negatives
⚙️
Parameters
Result —
❓
Frequently Asked Questions
What is the Matthews Correlation Coefficient?
The Matthews Correlation Coefficient (MCC) is a balanced measure used to evaluate binary classification models, especially when classes are of different sizes. It ranges from -1 to +1, where +1 indicates perfect prediction, 0 no better than random, and -1 an inverse prediction.
When should I use the Matthews Correlation Coefficient?
Use MCC when you have a binary classification problem with imbalanced classes. It provides a more reliable measure than accuracy in such cases.
How does the MCC differ from other metrics like precision and recall?
MCC considers all four quadrants of the confusion matrix (true positives, true negatives, false positives, and false negatives), making it a balanced metric that is not affected by class imbalance.
What does a negative MCC value indicate?
A negative MCC value indicates an inverse prediction, meaning the model’s predictions are opposite to the actual outcomes.
Can I use MCC for multi-class classification problems?
MCC is primarily used for binary classification. For multi-class problems, consider using other metrics like Cohen’s Kappa or macro/micro F1 scores.
How do I interpret the value of MCC?
Interpret MCC values as follows: +1 indicates a perfect prediction, 0 indicates no better than random guessing, and -1 indicates an inverse prediction.
What is the range of MCC values?
MCC values range from -1 to +1. The closer the value is to +1, the better the model’s performance.

Results are for informational purposes only and do not constitute professional advice.