Which metric measures the fraction of correct predictions made by a model?

Accuracy is a fundamental evaluation metric that reflects the overall performance of a classification model by calculating the fraction of correct predictions out of the total predictions made. It is defined mathematically as the number of correct predictions divided by the total number of predictions. Accuracy is particularly useful when the classes are balanced since it gives a clear indication of how well the model is performing in terms of identifying the correct categories.

In contrast, precision measures the number of true positive predictions divided by the number of total positive predictions, which focuses on the model's ability to avoid false positives. Recall, on the other hand, emphasizes the model's ability to find all relevant instances, calculated as the number of true positives divided by the number of actual positives. The F1 Score combines precision and recall into a single metric by taking their harmonic mean, providing a balance between the two.

While precision, recall, and F1 Score are valuable for assessing specific aspects of a model's performance, accuracy serves as a straightforward measure of correct predictions, making it the appropriate choice for the question posed.