From the course: Machine Learning with SageMaker by Pearson

Unlock this course with a free trial

Join today to access over 25,200 courses taught by industry experts.

Model evaluation metrics: Accuracy, precision, and recall

Model evaluation metrics: Accuracy, precision, and recall - Amazon SageMaker Tutorial

From the course: Machine Learning with SageMaker by Pearson

Start my 1-month free trial Buy for my team

Model evaluation metrics: Accuracy, precision, and recall

“

After we have created our model, we do need to ensure that it meets the performance requirements of whatever that project happens to be. So there are several metrics that we can monitor in order to determine if it is, again, meeting those performance requirements of whatever the project is, and it helps you identify by overfitting and underfitting and provide some insights into the model of how well it is performing with new data. So generalizing unseen data is an important feature of our model to monitor. So the key metrics for classification models, we have your accuracy, precision, recall, and F1 score. So accuracy is the overall correctness. And that is true positive plus true negative divided by the total. So we have this concept called a confusion matrix. And whenever you create a machine learning model, you feed it some data with a known outcome, meaning that if I ask you to predict X, and I think it should be labeled zero, and you return back to me that it is in fact predicted…

Contents