SAP interview Questions | Accuracy
Question
Is accuracy a good model for classification problems? Why so?
in progress
0
Machine Learning
4 years
3 Answers
760 views
Great Grand Master 0
Answers ( 3 )
Not always!!
Accuracy can be misleading. For example, in a problem where there is a large class imbalance, a model can predict the value of the majority class for all predictions and achieve a high classification accuracy. So, further performance measures are needed such as F1 score and Brier score.
Accuracy should not be considered in all the cases, especially when you are dealing with imbalanced data set.
According to the business problem at hand, you can consider other metrics like AUC,precision,recall,
F1-Score etc.
When we have an imbalanced dataset, we cannot use accuracy as a performance metrics. We can use precision, recall, or F1 score depending on the business case we are solving.