regression evaluation index
Mean Squared Error (MSE)
MSE (Mean Squared Error) is called mean squared error. Look at the formula
image.png
where y is on the test set.
Take the actual-predicted value and then square it and average it.
Take a look at this formula to see if it looks familiar. Isn't this the loss function of linear regression! ! ! Yes, our goal in linear regression is to minimize this loss function. Then the model is made, let's throw the loss function on the test set and see if the loss value is not good. Simple and intuitive violence!