查看更多>>摘要：This paper investigates the strategies contractors can employ to mitigate the exchange rate risks in hybrid payment systems. In our analysis, contractors face exchange rate risk, due to mismatches between their revenue and cost currencies, as well as property price risk, since they receive a portion of their revenue in the form of dwelling units. We rigorously compare the performance of three distinct risk models within the context of real estate development in Punta del Este, Uruguay. By evaluating these models against empirical data from a hypothetical project, our research provides valuable insights into their effectiveness in managing exchange rate risk. This addresses the critical need to validate risk models in the emerging real estate market of Punta del Este. Our analysis demonstrates a significant reduction in risk and higher expected profits compared with strategies that do not involve hedging.
du Toit, Hendrik AndriesSchutte, Willem DanielRaubenheimer, Helgard
21-47页
查看更多>>摘要：The use of machine learning algorithms in credit scoring can be enhanced by an improved understanding of the reasoning behind model decisions. Although machine learning algorithms are widely regarded as highly accurate, their use in settings that require an explanation of model decisions has been limited due to a lack of transparency. This is particularly the case in the banking sector, where the model risk frameworks of banks frequently require a significant level of model interpretability. In this paper, the Shapley value is evaluated as a machine learning interpretability technique in credit scoring. The Shapley value is a model-agnostic machine learning interpretability technique that quantifies the contribution of each feature in the prediction of a specific observation. The effectiveness of this technique is tested on various simulated data sets with covariates from different underlying distributions that are linearly and nonlinearly related to the outcome. Traditional models (eg, logistic and linear regression) and machine learning algorithms are trained on the data and the Shapley values are generated. Our results show that Shapley values are related to weights of evidence (a well-known measure in the scorecard literature) and can be used to explain the direction of relationships between explanatory variables and the outcome.
查看更多>>摘要：This study investigates the effects of online attention on corporate purchases of directors' and officers' (D&O) liability insurance. Using data from 2011 to 2021 on A-share Chinese listed firms, our theoretical analysis and empirical tests show that online attention increases purchases. The analysis and tests of the mediating mechanisms show that online attention increases insurance purchases by improving investor protection and exacerbating managerial career concerns. For the moderating mechanisms, our analysis and tests show that investors' visits to websites weaken the effect of online attention on liability insurance purchases, while corporate tax aggressiveness strengthens it. Our analysis and heterogeneity tests indicate that the increase in insurance purchases following online attention is more statistically significant in firms that have lower investor confidence, do not voluntarily disclose social responsibility information, are state-owned and face tighter financing constraints. The findings are of great significance for the improvement of the risk management system in China's capital markets.
查看更多>>摘要：Default prediction is of interest to the creditors, customers and suppliers of any firm as well as to policymakers and current and potential investors. Imbalanced classification for default prediction is considered a crucial issue. Therefore, this study proposes a default risk prediction model using a gradient-boosted decision tree (GBDT) based on the random undersampling (RUS) technique. We build a default prediction model based on 29 indicators and five different time windows. The model has two steps. First, the proposed RUS-GBDT model adopts the undersampling approach to generate different training samples based on the imbalance ratio of the training data. Then, the parameter of the GBDT is adaptively tuned with the area under the receiver operating characteristic curve of the predictive model for the selected training sample. We analyze the optimal imbalance ratio of the different training samples and compare the model's prediction performance with that of several other classification methods including logistic regression and support vector machines. Our experimental results demonstrate that the proposed model performs better than the other classifiers with respect to predicting and classifying the default status of listed companies in China.
NETL
NSTL
Incisive Media