Modeling Stated Severance-Pay Withdrawal Intentions in a Mandatory-Pension System: Interpretable Statistical Learning for Computational Actuarial Modeling
Mathematics · 13.11.2026 · 14 (22) · 4169
DOI: 10.3390/math14224169 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 13.11.2026. Verfasst von Shenhav Malul. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Pre-retirement withdrawal of pension-related severance capital may weaken retirement income adequacy. This study examines stated withdrawal intentions in Israel’s mandatory-pension system using a survey conducted from December 2023 to May 2024. The complete-case analytic sample comprises 421 salaried respondents with observed values for the four-category outcome and all 17 predictors. Seven classifiers were evaluated using stratified five-fold cross-validation repeated three times. Gradient boosting achieved the highest mean AUC (0.821), compared with 0.588 for additive logistic regression. A separate nested five-fold evaluation repeated four times, with tuning confined to inner folds, yielded a mean outer-fold AUC of 0.851 (SD 0.045). An additional spline-logistic benchmark, ordinal and multinomial regressions, and cross-fitted SHAP analyses examined model specification and interpretability. Pension centrality and impatience were the leading global SHAP features. These findings support nonlinear prediction of stated intentions, without implying observed withdrawals or causal effects.
Zitieren
APA
Malul, S. (2026). Modeling Stated Severance-Pay Withdrawal Intentions in a Mandatory-Pension System: Interpretable Statistical Learning for Computational Actuarial Modeling. Mathematics, 14(22), 4169. https://doi.org/10.3390/math14224169
Vancouver
Malul S. Modeling Stated Severance-Pay Withdrawal Intentions in a Mandatory-Pension System: Interpretable Statistical Learning for Computational Actuarial Modeling. Mathematics. 2026;14(22):4169. doi:10.3390/math14224169
BibTeX
@article{Malul2026,
author = {Malul, Shenhav},
title = {Modeling Stated Severance-Pay Withdrawal Intentions in a Mandatory-Pension System: Interpretable Statistical Learning for Computational Actuarial Modeling},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {22},
pages = {4169},
doi = {10.3390/math14224169}
}
EUVIMED