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

Bulletin of the National Research Centre

Table 7 Error measurements for individual base models and the stack ensemble model

Machine learning models
Metric	Stack ensemble	Random forest (RF)	XGBoost	Generalized linear model (GLM)	Decision tree (DT)	Neural network (NN)
RMSE	0.039143	1.761899	1.747702	1.758636	1.74786	1.803414
MAPE	0.02167	0.9773364	0.9798964	0.9851048	0.9799522	1.001618
MAE	0.0372259	1.669135	1.607744	1.623914	1.608126	1.704286

The stack ensemble consists of five base models: random forest (RF), XGBoost, generalized linear model (GLM), decision tree (DT), and neural network (NN)