New answers tagged bias
0
Yes, assuming you haven't overfitted on the test set (which may happen after extensive hyperparameter optimization), you can assume that your model has a MAPE of 15%.
However, if you limit the overfitting, the test performance would probably go down!
Top 50 recent answers are included
Related Tags
bias × 60machine-learning × 25
variance × 24
deep-learning × 6
overfitting × 6
svm × 5
xgboost × 5
neural-network × 4
dataset × 3
regression × 3
statistics × 3
random-forest × 3
training × 3
model-selection × 3
time-series × 2
predictive-modeling × 2
lstm × 2
linear-regression × 2
logistic-regression × 2
cross-validation × 2
machine-learning-model × 2
gradient-descent × 2
sampling × 2
perceptron × 2
weight-initialization × 2