Confusion Matrix

Typically, a confusion matrix treats a binary process of classification. The resulting table is composed of two rows and two columns, filled with four values – true positives, false positives, true negatives and false negatives.

In the confusion matrix, a true positive exists where observation is positive with a positive prediction. A false positive exists where observation is negative, with a positive prediction. A true negative exists where observation is negative with negative prediction, and a false negative indicates a positive observation with a negative prediction.

Assorted equations then show how to calculate accuracy and precision for a given project. Many confusion matrix projects will utilize tools like Python SciKit or Numpy or others.