January 31 · Article · Risks · Accounting
The rapid expansion of small and medium enterprise (SME) lending has intensified the need for accurate and interpretable credit risk forecasting. Financial institutions must anticipate potential business loan delinquency to maintain portfolio stability and meet regulatory standards. This study proposes an interpretable multi-model framework that integrates statistical (correlation screening and ordinary least squares regression), probabilistic (Gaussian Naïve Bayes), and classical time-series (SARIMA) methods to balance explanatory insight and predictive accuracy in delinquency forecasting. Ordinary least squares regression is used to quantify the direction and strength of each driver and yields statistically significant coefficients (β ≈ 1.336 for the overdue 15+ days bucket, p < 10−22). The Naïve Bayes classifier provides a probabilistic early-warning signal with an out-of-sample accuracy of 55%, precision of 43%, recall of 75%, and ROC AUC of 0.371. Finally, a seasonal ARIMA model fitted on the selected regressors achieves a mean absolute percentage error (MAPE) of 7.6% and an out-of-sample R2 of 0.49, demonstrating competitive forecasting performance while maintaining interpretability. The results show that the framework offers actionable insights for risk managers by identifying key risk drivers, providing probabilistic alarms, and generating calibrated point forecasts. The proposed approach contributes to the development of intelligent and explainable forecasting and control systems for modern financial institutions.
NANurken AbdurakhmanovOpen access
January 31 · Article · Sustainability · Artificial Intelligence
The intricate and dynamic nature of agricultural supply chains imposes stringent demands on optimization methodologies, necessitating multi-objective considerations, privacy safeguards, and decision transparency to address pivotal challenges in ensuring food security and sustainable development. This study introduces a Dynamic Heterogeneous Multi-Objective Graph Neural Network (DHMO-GNN) model, meticulously tailored for optimizing agricultural supply chains. It integrates five core modules: data preprocessing and heterogeneous graph construction, dynamic graph neural networks, multi-objective optimization, interpretability enhancement, and federated learning collaboration. The model adeptly captures temporal dynamics through sequential attention mechanisms and incremental updates, harmonizes cost, delivery time, and carbon emissions via multi-task learning and Pareto optimization, augments decision transparency with GNNExplainer and SHAP, and surmounts data silos by leveraging federated learning alongside differential privacy. Empirical evaluations on the Chengdu Hongguang Town Farmers’ Market dataset demonstrate that the centralized DHMO-GNN variant achieves a hypervolume indicator (HV) of 0.849, surpassing baseline models; the federated variant exhibits only a 2.6% decline under privacy constraints, underscoring its robustness. Ablation studies further corroborate the synergistic contributions of each module. This research furnishes an efficacious and trustworthy framework for the intelligent management of agricultural supply chains, holding profound implications for advancing digital transformation and green development.
BBBaurzhan BelgibaevOpen access
January 31 · Article · BMC Pregnancy and Childbirth · Public Health, Environmental and Occupational Health
BACKGROUND: Hyperemesis gravidarum is defined as intractable nausea and vomiting which occurs in 0.3–3% of all pregnancies. Data on hyperemesis in Russia are scarce. This study estimates the prevalence of hyperemesis gravidarum in pregnant women in two Arctic regions of European Russia. METHODS: A retrospective registry-based study was used. Data were collected from two population-based birth registries between 2006 and 2018. Bivariate associations between the prevalence of hyperemesis and potential determinants were studied via chi-squared tests. To assess factors contributing to the changes in the prevalence of hyperemesis over time, logistic regression models were applied. In total, 124,538 births composed the study base. RESULTS: The overall prevalence of hyperemesis was 2.4%. An inverse association was observed between maternal age and the prevalence of hyperemesis. Teenagers and women aged 20–24 years were more likely to have hyperemesis than women aged 25–29 years were (aOR = 1.32; 95% CI: 1.13 − 1.55 and aOR = 1.20; 95% CI: 1.08 − 1.34, respectively). The level of education did not influence the likelihood of developing hyperemesis. Being married, being primiparous, being underweight and having a female child were associated with hyperemesis. Women who reported no smoking during pregnancy were more likely to have hyperemesis after adjustment for other studied factors. CONCLUSIONS: The prevalence of hyperemesis in European Arctic Russia is greater than that in neighboring Nordic countries and varies over time. Changes in the prevalence of hyperemesis over time cannot be explained by changes in maternal sociodemographic characteristics during the study period.
AGAndrej GrjibovskiOpen access
