Due to the advanced technology associated with Big Data, data availability and computing power, most banks or lending institutions are renewing their business models. Credit risk predictions, monitoring, model reliability and effective loan processing are key to decision-making and transparency. In this work, we build binary classifiers based on machine and deep learning models on real data in predicting loan default probability. The top 10 important features from these models are selected and then used in the modeling process to test the stability of binary classifiers by comparing their performance on separate data. We observe that the tree-based models are more stable than the models based on multilayer artificial neural networks. This opens several questions relative to the intensive use of deep learning systems in enterprises.

The literature on the relationship between ESG disclosure and economic growth is relatively non-existent. Thus, this paper highlights the importance of taking this relationship into account in current sustainable policies. The main objective of extra-financial Disclosure is to mitigate Information Asymmetry. During this discussion, we show that ESG disclosure may not reduce information asymmetry as intended. We also show that complete extra-financial disclosure targeted by current policies is not optimal. There is an optimal disclosure threshold depending on the level of sustainable development of the country, the size of the companies and their development potential. Moreover, current ESG disclosure policies direct economies towards less polluting sectors, which is not necessarily optimal from an economic standpoint and could negatively affect economic activity and, therefore, the population’s well-being. We also provide some policy implications and suggestions for future research on the ESG disclosure literature.

Does machine learning and AI ensure that social biases thrive? This paper aims to analyze this issue. Indeed, as algorithms are informed by data, if these are corrupted, from a social bias perspective, good machine learning algorithms would learn from the data provided and reverberate the patterns learnt on the predictions related to either the classification or the regression intended. In other words, the way society behaves whether positively or negatively would necessarily be reflected by the models. In this paper, we analyze how social biases are transmitted from the data into banks loan approvals by predicting either the gender or the ethnicity of the customers using the exact same information provided by customers’ through their applications

The Fundamental Review of the Trading Book is a market risk measurement and management regulation recently issued by the Basel Committee. This reform, often referred to as “Basel IV”, intends to strengthen the financial system. The newest capital standard relies on the use of the Expected Shortfall. This risk measure requires to get sufficient information in the tails to ensure its reliability, as this one has to be alimented by a sufficient quantity of relevant data (above the 97.5 percentile in the case of the regulation or interest). In this paper, after discussing the relevant features of Expected Shortfall for risk measurement purposes, we present and compare several methods allowing to ensure the reliability of the risk measure by generating information in the tails. We discuss these approaches with respect to their relevance considering the underlying situation when it comes to available data, allowing practitioners to select the most appropriate approach. We apply traditional statistical methodologies, for instance distribution fitting, kernel density estimation, Gaussian mixtures and conditional fitting by Expectation-Maximisation as well as AI related strategies, for instance a Synthetic Minority Over-sampling Technique implemented in a regression environment and Generative Adversarial Nets.