We analyse financial stability and welfare impacts associated with the introduction of a Central Bank Digital Currency (CBDC) in a macroeconomic agent-based model. The model considers firms, banks, and households interacting on labour, goods, credit, and interbank markets. Households move their liquidity from deposits to CBDC based on the perceived riskiness of their banks. We find that the introduction of CBDC exacerbates bank-runs and may lead to financial instability phenomena. The effect can be changed by introducing a limit on CBDC holdings. The adoption of CBDC has little effect on macroeconomic variables but the interest rate on loans to firms goes up and credit goes down in a limited way. CBDC leads to a redistribution of wealth from firms and banks to households with a higher bank default rate. CBDC may have negative welfare effects, but a bound on holding enables a welfare improvement.

Credit scoring models face a critical challenge: severe class imbalance, with default rates typically below 10%, which hampers model learning and predictive performance. While synthetic data augmentation techniques such as SMOTE and ADASYN have been proposed to address this issue, the optimal augmentation ratio remains unclear, with practitioners often defaulting to full balancing (1:1 ratio) without empirical justification. This study systematically evaluates 10 data augmentation scenarios using the Give Me Some Credit dataset (97,243 observations, 7% default rate), comparing SMOTE, BorderlineSMOTE, and ADASYN at different multiplication factors (1x, 2x, 3x). All models were trained using XGBoost and evaluated on a held-out test set of 29,173 real observations. Statistical significance was assessed using bootstrap testing with 1,000 iterations. Key findings reveal that ADASYN with 1x multiplication (doubling the minority class) achieved optimal performance with AUC of 0.6778 and Gini coefficient of 0.3557, representing statistically significant improvements of +0.77% and +3.00% respectively (p = 0.017, bootstrap test). Higher multiplication factors (2x and 3x) resulted in performance degradation, with 3x showing a -0.48% decrease in AUC, suggesting a "law of diminishing returns" for synthetic oversampling. The optimal class imbalance ratio was found to be 6.6:1 (majority:minority), contradicting the common practice of balancing to 1:1. This work provides the first empirical evidence of an optimal "sweet spot" for data augmentation in credit scoring, with practical guidelines for industry practitioners and researchers working with imbalanced datasets. While demonstrated on a single representative dataset, the methodology provides a reproducible framework for determining optimal augmentation ratios in other imbalanced domains.

Risk management is a prominent issue in peer-to-peer lending. An investor may naturally reduce his risk exposure by diversifying instead of putting all his money on one loan. In that case, an investor may want to minimize the Value-at-Risk (VaR) or Conditional Value-at-Risk (CVaR) of his loan portfolio. We propose a low degree of freedom deep neural network model, DeNN, as well as a high degree of freedom model, DSNN, to tackle the problem. In particular, our models predict not only the default probability of a loan but also the time when it will default. The experiments demonstrate that both models can significantly reduce the portfolio VaRs at different confidence levels, compared to benchmarks. More interestingly, the low degree of freedom model, DeNN, outperforms DSNN in most scenarios.

Instance-dependent cost-sensitive (IDCS) classifiers offer a promising approach to improving cost-efficiency in credit scoring by tailoring loss functions to instance-specific costs. However, the impact of such loss functions on the stability of model explanations remains unexplored in literature, despite increasing regulatory demands for transparency. This study addresses this gap by evaluating the stability of Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) when applied to IDCS models. Using four publicly available credit scoring datasets, we first assess the discriminatory power and cost-efficiency of IDCS classifiers, introducing a novel metric to enhance cross-dataset comparability. We then investigate the stability of SHAP and LIME feature importance rankings under varying degrees of class imbalance through controlled resampling. Our results reveal that while IDCS classifiers improve cost-efficiency, they produce significantly less stable explanations compared to traditional models, particularly as class imbalance increases, highlighting a critical trade-off between cost optimization and interpretability in credit scoring. Amid increasing regulatory scrutiny on explainability, this research underscores the pressing need to address stability issues in IDCS classifiers to ensure that their cost advantages are not undermined by unstable or untrustworthy explanations.

There has been considerable interest in the regulation of artificial intelligence (AI), recently. It is increasingly recognized that so-called high-risk applications of AI, such as in Human Resources, Retail Banking, or within public schools, be it admissions or assessment, cannot be served by black-box AI systems with no human control. It is not clear [10], however, how to phrase even the desiderata for the regulation of AI. Here, we suggest that the desiderata could be the same as in the Civil Rights Act of 1964 and much of the subsequent civil-right legislation world-wide: equal treatment and equal impact. At the same time, we point out that these desiderata could be in conflict [34]. Let us illustrate the conflict on an example of a system that performs credit-risk estimate in a consumer-credit company.

The project to define what the late Marvin Minsky refers to as a suitcase word -- words that have so much packed inside them, making it difficult for us to unpack and understand this embedded intricacy in its entirety -- has not been without its fair share of challenges. The term does not have a single agreed-upon definition, with the dimensions of description shifting from optimization or efficient search space exploration to rationality and the ability to adapt to uncertain environments, depending on which expert you ask. The confusion becomes more salient when one hears news of machines achieving super-human performance in activities like Chess or Go -- traditional stand-ins for high intellectual aptitude -- but fail miserably in tasks like grabbing objects or moving across uneven terrain, which most of us do without thinking. But, several themes do emerge when we try to corner the concept. Our ability to explain why we do what we do makes a fair number of appearances in the list of definitions proposed by multiple disciplines.

The traditional approach to loan-portfolio management puts collections and overall performance on one side and origination on the other, with decisions that should be closely coordinated made by separate departments often deployed across distinct software systems. But that's changing as senior managers work to strengthen ties between departments and advances in artificial intelligence allow for more nuanced -- and more inclusive -- procedures for vetting would-be borrowers. Putting origination on an equal footing with other parts of loan management does more than provide holistic overviews. It puts extra resources into gatekeeping, providing a crucial first step in credit-risk evaluation and fraud detection, a must-have for overall portfolio health. It also equips lenders to compete in today's tough economic environment, a byproduct of business shutdowns, workplace furloughs and the general public's hesitancy to congregate in a pandemic.

Four weeks ago, my last article for The AI Journal pointed out that the COVID-19 "creates data deficits … Relaxed or suspended regulatory reporting requirements deliver less data to governments for aggregation, which in turn delivers less complete data sets to markets." It did not take long before the official sector started pointing out crucial breaks in key data sets used for global macro and credit risk analysis. De Nederlandsche Bank (the Dutch central bank) recently released research showing that key inputs for HIPC inflation measures were not collected during March and April. Because the HIPC data is only updated annually, when central bankers sought to plug the gap in order to conduct monetary policy, they only alternative was to use same-month 2019 data as a proxy for 2020 prices in key sectors disrupted by the pandemic. While the data gap was resolved, actual price data diverged significantly from the estimated data.

Bank of America Corp. has begun using artificial intelligence to predict the likelihood of companies defaulting on loans. "Today we present our inaugural work on applying the latest machine learning tools to analyzing the credit risk," Bank of America credit strategists Oleg Melentyev and Eric Yu and head of predictive analytics Toby Wade said in a research note Friday. They have started using natural language processing to digest earnings-calls transcripts in order to estimate companies' probability of default over the next 12 months. In expanding their default model with the help of AI, the credit strategists seek to detect language used by chief executive officers and chief financial officers that signals a company's high likelihood of default. Phrases that link to defaulting include cost cutting, asset sales, and cash burn, they said.

In this work we build a stack of machine learning models aimed at composing a state-of-the-art credit rating and default prediction system, obtaining excellent out-of-sample performances. Our approach is an excursion through the most recent ML / AI concepts, starting from natural language processes (NLP) applied to economic sectors' (textual) descriptions using embedding and autoencoders (AE), going through the classification of defaultable firms on the base of a wide range of economic features using gradient boosting machines (GBM) and calibrating their probabilities paying due attention to the treatment of unbalanced samples. Finally we assign credit ratings through genetic algorithms (differential evolution, DE). Model interpretability is achieved by implementing recent techniques such as SHAP and LIME, which explain predictions locally in features' space.