Skip to main content

Table 8 Comparison of predicted and actual values using stack ensembles with different numbers of base models

From: Improving mortality forecasting using a hybrid of Lee–Carter and stacking ensemble model

Year

2016

2016

2019

2019

Ensemble

Actual

Predicted

Actual

Predicted

Stack-3

 − 1.30684

 − 1.210258

 − 4.496415

 − 4.654073

Stack-4

 − 1.30684

 − 1.210264

 − 4.496415

 − 4.653921

Stack-5

 − 1.30684

 − 1.257513

 − 4.496415

 − 4.521541

  1. Increasing the number of base models leads to improved prediction accuracy