Computer scienceData scienceMachine learningEnsemble learning

Ensemble methods

Theory

Predicting with a stacked ensemble

Report a typo

To predict blood sugar levels in diabetes patients, you are stacking five different regression models.

You have learned that in order to obtain final prediction, predictions of the base models should be combined as follows:

y^final=0.05+0.1⋅y^1+0.2⋅y^2+0.1⋅y^3+0.3⋅y^4+0.3⋅y^5\hat{y}_{final} = 0.05 + 0.1 \cdot \hat{y}_{1} + 0.2 \cdot \hat{y}_{2} + 0.1 \cdot \hat{y}_{3} + 0.3 \cdot \hat{y}_{4} + 0.3 \cdot \hat{y}_{5},

where y^i\hat{y}_{i} is the prediction of the iith model.

Below are the predictions of the blood sugar level of a new patient obtained by each of the base models:

Base model (ii) Prediction (yi^\hat{y_i})
1 6.5
2 6
3 7
4 5.9
5 8

What will be the blood sugar level predicted by the stacked ensemble?

Enter a number
___

Create a free account to access the full topic