Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Wenjun Zhu has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Author Correction: Enduring impacts of El Niño on life expectancy in past and future climates

    by Yanbin Xu, Wenjun Zhu, Dhrubajyoti Samanta, Benjamin P. Horton

  • Top Cited Papers
    Open Access

    Enduring impacts of El Niño on life expectancy in past and future climates

    by Yanbin Xu, Wenjun Zhu, Dhrubajyoti Samanta, Benjamin P. Horton

    The El Niño–Southern Oscillation (ENSO) is a major driver of global climate variability, yet its long-term effect on life expectancy remains unclear. Here we quantify how ENSO persistently impedes mortality improvement, leading to considerable life expectancy and economic losses across high-income Pacific Rim countries. We estimate life expectancy losses of 0.5 years (monetary equivalent loss of US$2.6 trillion) for the 1982–1983 El Niño and 0.4 years (US$4.7 trillion) for the 1997–1998 event. Climate projections under moderate emissions pathways suggest a cumulative decline of 2.8 years in life expectancy by 2100, amounting to US$35 trillion losses, with most of the monetary burden falling on the middle-aged population. These findings reveal that intensifying ENSO variability poses an underrecognized and enduring threat to human health and socio-economic stability, underscoring the urgent need for targeted adaptation strategies to safeguard population well-being.


  • Open Access

    Quantile-based Interpretable Neural Network Models: Mortality Forecasting and Actuarial Simulations

    by Yang Qiao, Jinggong Zhang, Wenjun Zhu, Chou‐Wen Wang

    This paper introduces a class of quantile-based, interpretable neural network (NN) models for mortality prediction: the Lee-Carter neural network (LCNN) model, the Renshaw-Haberman neural network (RHNN) model, and the simple neural network (simpleNN) model that balances simplicity with predictive performance. These models preserve the linear interpretability of classic stochastic mortality models while harnessing the flexibility of NNs to capture complex nonlinear patterns in mortality data, thereby achieving enhanced predictive performance. Leveraging a composite loss function that integrates pinball, median anchoring, and quantile-crossing penalty terms, we estimate mortality quantiles and develop an efficient simulation scheme based on interpolation. This framework provides distributional insights essential for pricing, reserving and risk management. Extensive empirical analyses across multiple populations demonstrate that the proposed models consistently outperform traditional approaches in predictive accuracy. We further illustrate their practical utility through an application to longevity swap pricing.

  • Open Access

    Modeling mortality with Kernel Principal Component Analysis (KPCA) method

    by Yuanqi Wu, Andrew Chen, Yanbin Xu, Guangming Pan, Wenjun Zhu

    As the global population continues to age, effective management of longevity risk becomes increasingly critical for various stakeholders. Accurate mortality forecasting serves as a cornerstone for addressing this challenge. This study proposes to leverage Kernel Principal Component Analysis (KPCA) to enhance mortality rate predictions. By extending the traditional Lee-Carter model with KPCA, we capture nonlinear patterns and complex relationships in mortality data. The newly proposed KPCA Lee-Carter algorithm is empirically tested and demonstrates superior forecasting performance. Furthermore, the model’s robustness was tested during the COVID-19 pandemic, showing that the KPCA Lee-Carter algorithm effectively captures increased uncertainty during extreme events while maintaining narrower prediction intervals. This makes it a valuable tool for mortality forecasting and risk management. Our findings contribute to the growing body of literature where actuarial science intersects with statistical learning, offering practical solutions to the challenges posed by an aging world population.


  • Managing Weather Risk with a Neural Network-Based Index Insurance

    by Zhanhui Chen, Yang Lu, Jinggong Zhang, Wenjun Zhu

    Weather risk affects the economy, agricultural production in particular. Index insurance is a promising tool to hedge against weather risk, but current piecewise-linear index insurance contracts face large basis risk and low demand. We propose embedding a neural network-based optimization scheme into an expected utility maximization problem to design the index insurance contract. Neural networks capture a highly nonlinear relationship between the high-dimensional weather variables and production losses. We endogenously solve for the optimal insurance premium and demand. This approach reduces basis risk, lowers insurance premiums, and improves farmers’ utility. This paper was accepted by Agostino Capponi, finance. Funding: This work was supported by the Research Grants Council, University Grants Committee [Grants GRF 16502020, GRF 16504522, and T31-603/21-N], Singapore Ministry of Education Academic Research Fund Tier 1 [Grants RG143/19 and RG55/20], the Natural Sciences and Engineering Research Council of Canada [Grants RGPIN-2021-04144 and DGECR-2021-00330], the Research Database Matching Fund, and the School of Business and Management, Hong Kong University of Science and Technology. Supplemental Material: The data files and online appendices are available at https://doi.org/10.1287/mnsc.2023.4902 .


  • Digital financial inclusion and domestic tourism demand: Through the lens of spatial spillover

    by Yanzhao Li, Ju-E Guo, Wenjun Zhu

    Domestic tourism demand has dominated the global tourism market and has been more resilient during the COVID-19 pandemic; yet, it is under-studied compared to international tourism demand. Digital financial inclusion (DFI) enables the provision of formal financial products and services to small and medium-sized tourism enterprises and tourists through cost-effective digital means, potentially boosting domestic tourism demand. Integrating micro- and macro-level data from 335 prefecture-level regions in China, we investigate the impact of DFI on domestic tourism demand using spatial panel models. Our analysis reveals significant and positive effects, both direct and spillover, of DFI on domestic tourism demand within a region and across regions. Notably, among the three dimensions of DFI, the usage depth exhibits the most substantial spillover effects. Furthermore, our findings also highlight the crucial role of DFI in internalizing domestic tourism revenues. Our study provides practical implications for sustainable domestic tourism development in the digital era.


  • Open Access

    Characteristics and Predictive Modeling of Short-term Impacts of Hurricanes on the US Employment

    by Gan Zhang, Wenjun Zhu

    This study examines the short-term employment changes in the US after hurricane impacts. An analysis of hurricane events during 1990-2021 suggests that county-level employment changes in the initial month are small on average, though large employment losses (>30%) can occur after extreme storms. The overall small changes are partly a result of compensation among different employment sectors, such as the construction and leisure and hospitality sectors. Employment losses tend to be relatively pronounced in the service-providing industries. The post-storm employment shock is negatively correlated with the metrics of storm hazards (e.g., extreme wind and precipitation) and geospatial details of impacts (e.g., storm-entity distance). Additionally, non-storm factors such as county characteristics also strongly affect short-term employment changes. The findings inform predictive modeling of short-term employment changes, which shows promising skills for service-providing industries and high-impact storms. The Random Forests model, which can account for nonlinear relationships, greatly outperforms the multiple linear regression model commonly used by economics studies. These findings may help improve post-storm aid programs and the modeling of hurricanes socioeconomic impacts in a changing climate.


  • A Deep Factor Model for Crop Yield Forecasting and Insurance Ratemaking

    by Wenjun Zhu

    Effective agricultural insurance and risk management programs rely on accurate crop yield forecasting. In this article, a novel deep factor model for crop yield forecasting and crop insurance ratemaking is proposed. This framework first utilizes a deep autoencoder to extract a latent factor, called the production index, that integrates salient spatial temporal patterns in the original yield data. Then, a concatenated deep learning model is constructed to enhance the modeling of the production index and the reconstruction of crop yields. Convolutional neural networks are employed to capture the high-dimensional and highly nonlinear structure within the crop yield data, as well as its interactions with weather and economic variables. The proposed deep factor framework is applied to the county-level data in the state of Iowa. Empirical results show that the newly proposed deep factor model significantly improves the prediction accuracy, especially in the test set. Based on a retain–cede crop insurance rating game between a private insurer and the government, we show that the proposed deep factor model provides economically and statistically significant improvement over the current Risk Management Agency ratemaking methodology.