thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Foundational

Accuracy

The fraction of all predictions that are correct: (TP + TN) / total.

Definition

Accuracy is intuitive but misleading on imbalanced datasets, where always predicting the majority class can score highly. It is appropriate when classes are balanced and error costs are similar.

Example

A model that predicts not-fraud for every transaction is 99.5% accurate if fraud is 0.5%.

Exam tip

Reject accuracy as the metric when the dataset is imbalanced.

Related terms