Credit risk assessment is at the core of modern economies. Traditionally, it is measured by statistical methods and manual auditing. Recent advances in financial artificial intelligence stemmed from a new wave of machine learning (ML)-driven credit risk models that gained tremendous attention from both industry and academia. In this paper, we systematically review a series of major research contributions (76 papers) over the past eight years using statistical, machine learning and deep learning techniques to address the problems of credit risk. Specifically, we propose a novel classification methodology for ML-driven credit risk algorithms and their performance ranking using public datasets. We further discuss the challenges including data imbalance, dataset inconsistency, model transparency, and inadequate utilization of deep learning models. The results of our review show that: 1) most deep learning models outperform classic machine learning and statistical algorithms in credit risk estimation, and 2) ensemble methods provide higher accuracy compared with single models. Finally, we present summary tables in terms of datasets and proposed models.

This article examines the role of country-specific sources of output and interest rate or exchange rate volatility in driving Foreign Direct Investment (FDI) activities. Building on a dataset with bilateral FDI flows among 24 Organization for Economic Co-operation and Development (OECD) economies over the period 1985–2007, we find that nominal and real volatility strongly deter foreign investments. Output and exchange rate volatility matter in particular for the decision whether to invest in a foreign country in the first place. Interest rate volatility mainly influences the amount of foreign investments.

This paper investigates the impact of platform-based accommodations in the real estate market on socio-economically relevant indicators. Using a city-specific dataset from 2017 to 2019 we studied the effect of Airbnb density on rental prices, residential population, and non-local undergraduate enrollments in the municipality of Bologna. Leveraging rental estimates from the Real Estate Market Observatory, as well as data on Airbnb listings, we employed three longitudinal estimations with zone-fixed effects and various demographic and economic controls. Our analysis reveals a significant positive association between Airbnb and rental prices. Moreover, Airbnb presence seems to have a negative impact on non-resident undergraduate enrollments in the subsequent year. These findings support existing literature on the impact of platform-based accommodations on rent and underscore its potential role in producing tourist-led gentrification within urban areas.

We compare in a backtesting study the performance of univariate models for Value-at-Risk (VaR) and expected shortfall based on stable laws and on extreme value theory (EVT). Analyzing these different approaches, we test whether the sum - stability assumption or the max - stability assumption, that respectively imply alpha-stable laws and Generalized Extreme Value (GEV) distributions, is more suitable for risk management based on VaR and expected shortfall. Our numerical results indicate that alpha-stable models tend to outperform pure EVT-based methods (especially those obtained by the so-called block maxima method) in the estimation of Value-at-Risk, while a peaks-over-threshold method turns out to be preferable for the estimation of expected shortfall. We also find empirical evidence that some simple semiparametric EVT-based methods perform well in the estimation of VaR.