This paper uses a generalised stacking method to introduce a novel hybrid model that combines a one-dimensional convolutional neural network 1DCNN with extreme gradient boosting XGBoost. We compared the predictive accuracies of the proposed hybrid architecture with three conventional algorithms-1DCNN, XGBoost and logistic regression (LR) using a dataset of over twenty thousand peer-to-peer (P2P) consumer credit observations. By leveraging the SHAP algorithm, the research provides a detailed analysis of feature importance, contributing to the model’s predictions and offering insights into the overall and individual significance of different features. The findings demonstrate that the hybrid model outperforms the LR, XGBoost and 1DCNN models in terms of classification accuracy. Furthermore, the research addresses concern regarding fairness and bias by showing that removing potentially discriminatory features, such as age and gender, does not significantly impact the hybrid model’s classification capabilities. This suggests that fair and unbiased credit scoring models can achieve high effectiveness levels without compromising accuracy. This paper makes significant contributions to academic research and practical applications in credit risk management by presenting a hybrid model that offers superior classification accuracy and promotes interpretability using the model agnostic SHAP framework.

There is a growing concern about the high degree of non-technical losses (NTL) in developing countries especially sub-saharan Africa. Whereas several studies have employed artificial intelligence (AI) to analyze NTL, a major drawback in these studies is the focus on customer data only without considering the possible contribution of electricity distribution staff to NTL. This study introduces a novel approach to NTL reduction by analyzing a combined dataset of staff operational processes and customer consumption data. A deep-learning architecture called non-technical losses convolutional neural network (NTLCONVNET) was developed which consists of a series of three one-dimensional convolutional neural networks (1D-CNN) with different depths combined with several fully connected layers. Furthermore, limited or no research has studied the decision rationale influencing how AI models interpret the significance of features in predicting NTL. To achieve the explainability of the model, SHapley Additive exPlanations (SHAP) kernel and tree-based explainers were used for the deep and ensemble learning models respectively to determine the relative importance of the variables and how they contribute to the overall model prediction. A novel ranking framework was used to compute the holistic ranking of the variables across multiple models. The finding suggests that the staff-related variables omitted in the extant literature are significant predictors of NTL. The NTLCONVNET was compared with 5 ensemble learning algorithms and the results show that the NTLCONVNET significantly surpasses all other models, scoring 0.844, 0.838, 0.836 and 0.836 on weighted average Precision, Recall, f1 and accuracy respectively. This study suggests a policy outcome of introducing human resource metrics into NTL reduction strategies.

This study empirically investigates the relationship between board composition, focusing on board size and board independence, and firm performance. It further examines how national governance quality moderates this relationship. Using a panel dataset of 1604 firms from 41 developed and emerging economies, the study employs pooled ordinary least squares (OLS) as the baseline regression method, alongside two-stage instrumental variable regression and system generalised method of moments (GMM) to address potential endogeneity concerns. Firm performance is measured using return on equity (ROE) and Tobin’s Q. Board size is captured by the number of directors on the board, while board independence is measured by the proportion of non-executive directors. The findings indicate that while board size and independence are positively associated with firm performance, the strength of these relationships weakens in countries with high governance quality. Our findings remain robust after controlling for dynamic endogeneity and unobserved time-invariant heterogeneity inherent in the corporate governance–performance nexus.

The prevailing view is that ESG performance contributes to corporate financial stability, particularly regarding long-term sustainability objectives. However, there is a notable lack of critical research exploring its short-term financial effects, especially within capital-intensive sectors experiencing green transformation. This study examines the theoretical gap by investigating whether increased ESG performance may unintentionally heighten the financial burden and default risk in the short run. To verify the stability of each variable in the series, we employed the short-panel unit root test on panel data from 234 Chinese energy industry companies covering the years 2015 to 2023. Including enterprise fixed effects as well as time fixed effects, we find that higher ESG ratings increase the possibility of default risk in the Chinese energy sector. This effect remains robust after controlling firm size, financial leverage, return on assets, return on equity, earnings per share, beta and firm age. In addition, we conduct robustness checks using alternative default risk measures, both endogeneity- and component-based, and the outcomes demonstrate that the impact is substantial and consistent. Consequently, we may draw the conclusion that raising the ESG rating has an adverse effect on reducing corporate default risk, which fills the knowledge gap regarding the influence of listed companies’ default risk on China’s energy sector. Moreover, it has been found that green innovation plays a strengthening role in the analysis of the interaction term between green innovation and ESG on default risk. This suggests that while green innovation is a strategic initiative aimed at long-term sustainability, it requires a significant amount of capital and resources in the short term, which may result in higher default risk in the beginning.

The goal of this paper is to illustrate how Nigerian banks, and indeed banks elsewhere, can develop solutions that incorporate both BI and predictive analytics