Tree-Based Machine Learning Methods for Modeling and Forecasting Mortality

Abstract

Machine learning has recently entered the mortality literature in order to improve the forecasts of stochastic mortality models. This paper proposes to use two pure, tree-based machine learning models: random forests and gradient boosting, based on the differenced log-mortality rates to produce more accurate mortality forecasts. These forecasts are compared with forecasts from traditional, stochastic mortality models and with forecasts from random forests and gradient boosting variants of the stochastic models. The comparisons are based on the Model Confidence Set procedure. The results show that the pure, tree-based models significantly outperform all other models in the majority of cases considered. To address the lack of interpretability issue associated with machine learning models, we demonstrate how to extract information about the relationships uncovered by the tree-based models. For this purpose, we consider variable importance, partial dependence plots, and variable split conditions. Results from the in-sample fit suggest that tree-based models can be very useful tools for detecting patterns within and between variables that are not commonly identifiable with traditional methods.

Modelling socio-economic mortality at neighbourhood level

“…This approach offers a high degree of flexibility, does not require assumptions about the underlying relationship between predictive variables, and we show that it is an effective tool for analysing large and complex mortality datasets. The random forest estimator is a well-understood and widely used method from machine learning, and it has been applied in mortality modelling as an alternative to parametric models, see for example, Bjerre (2022), Hong et al (2021), Levantesi and Nigri (2020) and Levantesi and Pizzorusso (2019). While those authors apply the random forest method to improve the goodness-of-fit and the predictive power of mortality models, we use the method to analyse the impact of socio-economic characteristics on higher or lower mortality in any given neighbourhood compared to the national mortality levels for a population with a similar age structure.…”

“…This approach offers a high degree of flexibility, does not require assumptions about the underlying relationship between predictive variables, and we show that it is an effective tool for analysing large and complex mortality datasets. The random forest estimator is a well-understood and widely used method from machine learning, and it has been applied in mortality modelling as an alternative to parametric models, see for example, Bjerre (2022), Hong et al . (2021), Levantesi and Nigri (2020) and Levantesi and Pizzorusso (2019).…”

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

“…To address these limitations, the applications of machine learning have emerged as a potential remedy. This has been pointed out by researchers such as (Bjerre 2022;Marino et al 2023;Nigri et al 2019). Machine learning techniques offer a more adaptable and data-centric approach to modeling mortality trends, capable of capturing complex interactions and nonlinear relationships between variables and mortality outcomes (Berrang-Ford et al 2021).…”