Key points are not available for this paper at this time.
Population aging and low fertility are threatening the fiscal sustainability of China’s public pension system. To reduce the fiscal pressure, the Chinese government has established a personal pension system and introduced the delayed retirement policy. Based on 576 valid survey responses from China, this study integrates partial least squares structural equation modeling (PLS-SEM) and artificial neural networks (ANN) to examine the relationship between the delayed retirement policy and personal pension participation. The results indicate that the perceptions of delayed retirement policy are directly associated with individuals’ willingness to participate in personal pensions and indirectly related to it through attitude, subjective norm, and perceived behavioral control. The ANN further supports the robustness of the structural equation model and ranks the relative importance of predictors in participation behavior. Theoretically, this study extends the explanatory power of TPB in explaining behavioral responses to policy reforms. It also demonstrates the complementarity of structural equation modeling and artificial intelligence techniques. Practically, the findings offer insights for enhancing coordination between delayed retirement and personal pension systems.
Chen et al. (Sat,) studied this question.