This paper proposes different classification algorithms—logistic regression, support vector machine, K-nearest neighbors, and random forest—in order to identify which candidates are likely to default for a credit scoring model. Three different feature selection methods are used in order to mitigate the overfitting in the curse of dimensionality of these classification algorithms: one filter method (Chi-squared test and correlation coefficients) and two wrapper methods (forward stepwise selection and backward stepwise selection). The performances of these three methods are discussed using two measures, the mean absolute error and the number of selected features. The methodology is applied for a valuable database of Taiwan. The results suggest that forward stepwise selection yields superior performance in each one of the classification algorithms used. The conclusions obtained are related to those in the literature, and their managerial implications are analyzed.

This paper examines the increasing importance of green, social and sustainable bonds in the financial markets. We first detail the theoretical framework, introducing sustainable development and green finance; relating green bonds to both ecological economics literature, and the central banks perspective; and, finally, analyzing the green bonds efficiency as a financial resource. Afterwards, we estimate the effect of green bond issues on the companies share’s price. So we collect the companies share’ prices around the announcement of the issue. Then we build an event time window with different time ranges before and after the announcement with the accumulated returns in order to be able to observe the reaction in the market in different stages. We demonstrate that the announcement of a green bond has a positive reaction in the market by increasing the return on shares of green bond issuing

This study presents a methodology for forecasting the medium– and long–term real revenues of the automotive post–sales service sectors, assuming the automobile industry is nowadays undergoing a deep process of transformation. There are several conditioning factors, usage as well as environmental reasons, that makes past times an unreasonable guide for a future forecast. Firstly, we estimate, using regression models, the most important variables for the automobile sector that will affect the long–term forecasts of the automotive aftermarket’s revenues. Secondly, we apply participatory methods to quantify the impact of the new conditioning factors. This is a research tool used for the Spanish automotive aftermarket. Our results indicate how stakeholders’ perceptions modulate the forecasts for those economic sectors involved in a disrupted changing business model.

This paper applies a new artificial intelligence architecture, the temporal fusion transformer (TFT), for the joint GDP forecasting of 25 OECD countries at different time horizons. This new attention-based architecture offers significant advantages over other deep learning methods. First, results are interpretable since the impact of each explanatory variable on each forecast can be calculated. Second, it allows for visualizing persistent temporal patterns and identifying significant events and different regimes. Third, it provides quantile regressions and permits training the model on multiple time series from different distributions. Results suggest that TFTs outperform regression models, especially in periods of turbulence such as the COVID-19 shock. Interesting economic interpretations are obtained depending on whether the country has domestic demand-led or export-led growth. In essence, TFT is revealed as a new tool that artificial intelligence provides to economists and policy makers, with enormous prospects for the future.

This paper examines the sensitivity of firms’ R&D expenditures to being externally financial constrained to undertake innovation projects, considering that being constrained is endogenous. It focuses on devising a model that enable us to explore the combined impact of liquidity constraints, demand shocks, and credit cycle on the cyclically of R&D, controlling by the firms characteristics. The methodology proposed consists of jointly estimating three interrelated equations with mixed distributions of dependent variables. The results obtained complete and improve those of the previous research. It is found that the effect of the business cycle on the perception of external financial constraints is subject to the availability of internal funds in each firm. On the other hand, constrained firms expend in R&D halve of the unconstrained ones, and the sensitivity of firms’ R&D expending to GDP is countercyclical in firms with low cash flows and procyclical in firms with high cash flows. The R&D expending of firms is negatively associated with the aggregate leverage ratio of the non-financial sector. These results mean that business decisions, in particular R&D expending decisions, and macroeconomic variables are strongly related. A better understanding of these interrelations should help in designing macroeconomic policies aimed at stabilizing the economy and reduce growth volatility.