Accurate prediction of loan defaults is a central challenge in credit risk management, particularly in modern financial datasets characterised by nonlinear relationships, class imbalance, and evolving borrower behaviour. Traditional statistical models and static ensemble methods often struggle to maintain reliable performance under such conditions. This study proposes an Optimised Greedy-Weighted Ensemble framework for loan default prediction that dynamically allocates model weights based on empirical predictive performance. The framework integrates multiple machine learning classifiers, with their hyperparameters first optimised using Particle Swarm Optimisation. Model predictions are then combined via a regularised greedy weighting mechanism. At the same time, a neural-network-based meta-learner is employed within stacked-ensemble to capture higher-order relationships among model outputs. Experiments conducted on the Lending Club dataset demonstrate that the proposed framework improves predictive performance compared with individual classifiers. The BlendNet ensemble achieved the strongest results with an AUC of 0.80, a macro-average F1-score of 0.73, and a default recall of 0.81. Calibration analysis further shows that tree-based ensembles such as Extra Trees and Gradient Boosting provide the most reliable probability estimates, while the stacked ensemble offers superior ranking capability. Feature analysis using Recursive Feature Elimination identifies revolving utilisation, annual income, and debt-to-income ratio as the most influential predictors of loan default. These findings demonstrate that performance-driven ensemble weighting can improve both predictive accuracy and interpretability in credit risk modelling. The proposed framework provides a scalable data-driven approach to support institutional credit assessment, risk monitoring, and financial decision-making.
Cardiovascular disease (CVD) is the leading cause of death worldwide, wreaking havoc in both developed and developing countries. Hypertension (HPT) is the leading cause of death and the third leading cause of disability-adjusted life years. HPT cases are increasing in the Ejisu Municipality, but there is a lack of accurate information on hypertension and its determinants in the municipality. The purpose of this study was to find out how common hypertension is and what factors contribute to it in rural adults in Ejisu Municipality.This study used a descriptive cross-sectional study design, with a structured questionnaire administered via face-to-face interviews, to residents of fourteen rural communities in the municipality. Simple random sampling was used to select community-level participants for the study.The collected data was entered into Microsoft Excel, cleaned and exported to Stata/SE version 14.0 for analysis. Chi-squared tests were used to determine the relationship between the quantitative and independent variables. The strength of association was determined using multivariable logistic regression analysis.The study showed a prevalence rate of 28.9% hypertension among rural residents. Females (64.89%) were found to be more hypertensive compared to males (35.11%). Risk factors significantly associated with hypertension among the study population were age, family history, and smoking.
While people often resist suggestions when their autonomy is challenged, the reluctance to use chatbot services due to perceived threats to freedom of choice remains unexplored. Based on psychological reactance theory, this study investigates the effects of personalized recommendations by AI chatbots, focusing on how they could lead to chatbot avoidance. An online survey collects data from 186 participants who had experience using chatbot services during online shopping. The results of bootstrapping analysis show that personalized recommendations by chatbots increase avoidance behavior, serially mediated by perceived threats to freedom and negative affect. The study also finds the interplay effect of the personalized recommendations of chatbots and fashion involvement on the threat to freedom. When consumers have low fashion involvement, personalized recommendations by a chatbot decrease the threat of freedom. However, when consumers have high fashion involvement, the personalized recommendations of chatbots increase their perceptions of the threat of freedom. This research contributes to the understanding of negative consumer responses to AI chatbots in retail, offering insights into how personalized recommendations can be perceived as intrusive and impact consumer acceptance negatively.
We measure for the first time the differential photoproduction cross section d sigma/dt of the a(2) (1320) meson at an average photon beam energy of 8.5 GeV, using data with an integrated luminosity of 104 pb(-1) collected by the GlueX experiment. We fully reconstruct the gamma p -> eta pi(0)p reaction and perform a partial-wave analysis in the a(2) (1320) mass region with amplitudes that incorporate the linear polarization of the beam. This allows us to separate for the first time the contributions of natural- and unnatural-parity exchanges. These measurements provide novel information about the photoproduction mechanism, which is critical for the search for spin-exotic states.
