Forecasting recovery rates on non-performing loans with machine learning

We compare the performance of a wide set of regression techniques and machine-learning algorithms for predicting recovery rates on non-performing loans, using a private database from a European debt collection agency. We find that rule-based algorithms such as Cubist, boosted trees, and random forests perform significantly better than other approaches. In addition to loan contract specificities, predictors that refer to the bank recovery process — prior to the portfolio’s sale to a debt collector — are also shown to enhance forecasting performance. These variables, derived from the time series of contacts to defaulted clients and client reimbursements to the bank, help all algorithms better identify debtors with different repayment ability and/or commitment, and in general those with different recovery potential.     

Factors that influence the consumption of food outside the home in Brazil

The food sector has taken on an unprecedented dynamism in recent years. The processing and distribution of food, although heavily influenced by tradition, have seen intensive innovations, leading to changes in the way individuals consume. One of these changes is the consistent growth of the habit of eating outside the home. Consuming food outside the home involves a number of practices such as eating at commercial establishments that specialize in food (restaurants, fast food restaurants and snack bars) and those that offer food as a part of their services (hotels, in‐flight meals), and non‐commercial alternatives such as the homes of family and friends. In order to describe the eating habits of consumers in the town of Lavras in Minas Gerais State, Brazil, especially when it comes to eating outside the home, a quantitative study was conducted, with 413 questionnaires being distributed by convenience sampling. Among the main results are: (a) a search for variety as a motivator for eating outside the home; (b) convenience as an important element on many occasions of consumption; (c) more intensive consumption and more favourable attitudes towards eating out on the part of younger people, people with higher incomes, no children and a higher degree of schooling; (d) importance of paying for food by the kilo. When compared with a study conducted in England, important similarities were identified in socio‐demographic influences, although the cultural factors are notable when it comes to dishes and the types of eating establishment. The growing habit of eating out has therefore become a worldwide phenomenon, but with cultural and regional differences that have led to different rhythms in terms of change and the way food is supplied. The recovery of embedded cultural habits, with increased value being given to slow food, traditional dishes and tradition itself, appears to co‐exist with a productivity model of food courts, pasteurization and accessible prices. The occasion for consumption, which may be understood as the dichotomies of ‘weekday versus weekend’ or ‘convenience versus leisure’, is an important element that influences consumer behaviours. The undertaking of a cross‐cultural comparative study can be seen as an important step in this field of research.     

Cost of capital and public loan guarantees to small firms

In this paper, we study the determinants of the spread charged by banks under a UK policy intervention scheme, aimed at supporting access to the credit market for small firms through guarantee backed loans. We exploit a unique dataset containing data on 29,266 guarantee backed loans under the UK SFLG scheme over the period 2000 to 2005. Results suggest that lower spreads are offered for loans of larger amounts and higher durations, for service firms, for larger firms, and for those located in the most advanced regions. Higher spreads are applied to high-tech manufacturing firms and to loans issued for working capital purposes. We also find that the presence of other extant debt is associated with a relatively higher spread and that this effect is especially significant for the subset of firms that have reached a maximum debt capacity based on collateralized assets. Further, we also find that the higher the incidence of the publicly guaranteed debt over the total amount of outstanding loans, the lower, on average, the spread. However, an increase in the guaranteed coverage leads to a contraction in the spread only for loans aimed at covering working capital needs rather than investments.     

Growth of born globals: the role of the entrepreneur’s personal factors and venture capital

This paper examines to what extent the human capital of entrepreneurs and the receipt of venture capital (VC) financing affect the growth of born globals (BGs). The study analyzes a sample of 242 BGs resulting from a survey on high-tech start-ups operating in the ICT and electronics sectors, located in different countries throughout the world. A multivariate explorative analysis controlling for the endogenous nature of VC is conducted. The results indicate that the experience of the entrepreneur in having previously established another entrepreneurial firm positively affects the growth of BGs. A negative effect is associated with the presence of heterogeneity in the management team in terms of education background. With regard to the linkage between financial capital and growth, it is found that both VC financing and the number of founders (a proxy for the availability internal capital) positively influence the growth of BGs.     

Institutions and Firms' Productivity: Evidence from Electricity Distribution in the EU

Firms' productivity is influenced by internal and external institutions. Ownership is the core internal institutional feature of the firm, while the most important external institutional feature is the quality of government, which shapes the environment in which firms operate. We explore the relative role of these factors and their interaction in determining total factor productivity of electricity distribution firms in 16 EU countries. Using data from the Amadeus database of balance‐sheet information and from the Quality of Governance database, we find that when the quality of government is poor, public ownership is associated with lower productivity levels; however, public ownership is associated with higher productivity in countries characterized by higher quality of the institutional environment.     

A Value at Risk Approach to Background Risk

This paper studies the effects of an uninsurable background risk (BR) on the demand for insurance (proportional and with deductible). We study both the case of BR uncorrelated with the insurable one and the perfectly correlated one, in a Gaussian world. In order to perform our study, we exploit the new risk measure known as Value at Risk (VaR) and consider insurance contracts which are Mean-VaR efficient. We obtain results which depend on the parameters (moments) of both risks and on the magnitude of loadings charged by the insurance company, instead of depending on the risk attitudes of the insured, such as risk aversion and prudence.We demonstrate that, if loadings are not too high, the demand for insurance increases with positively correlated BR; it decreases with BR negatively correlated if the latter is less risky than the insurable one (in this case it can even go to zero, if loadings are too high); it goes to zero with BR which is negatively correlated and more risky than the insurable one.     

On the short-time behavior of the implied volatility for jump-diffusion models with stochastic volatility

In this paper we use Malliavin calculus techniques to obtain an expression for the short-time behavior of the at-the-money implied volatility skew for a generalization of the Bates model, where the volatility does not need to be a diffusion or a Markov process, as the examples in Sect. 7 show. This expression depends on the derivative of the volatility in the sense of Malliavin calculus. E. Alòs’ research is supported by grants MEC FEDER MTM 2006 06427 and SEJ2006-13537. J.A. León’s research is partially supported by the CONACyT grant 45684-F. J. Vives’ research is supported by grant MEC FEDER MTM 2006 06427.     

Feeling capable and valued: A prosocial perspective on the link between empathy and social entrepreneurial intentions

Empathy is a key trait distinguishing social entrepreneurs from traditional entrepreneurs, and an important antecedent of social entrepreneurial (SE) intentions. Yet, little research explains the mechanisms through which empathy motivates SE intentions. We argue that studying the link between the prosocial trait of empathy and the prosocial outcome of SE intentions requires a prosocial lens that traditional entrepreneurial intent theories cannot offer. Building on prosocial motives research, we propose that empathy explains SE intentions through two complementary mechanisms: self-efficacy (an agentic mechanism), and social worth (a communal mechanism). We find support for our hypotheses in a study of 281 university students.     

FIRM HETEROGENEITY,RULES OF ORIGIN,AND RULES OF CUMULATION*

This article sheds light on the restrictive nature of rules of origin (ROO) and on the role of diagonal cumulation in mitigating the protectionist content of ROO. Empirical evidence suggests that diagonal cumulation has beneficial effects on trade—particularly among spoke countries. We show that these patterns can be reconciled with a theoretical setting where heterogeneous firms buy intermediate inputs from domestic and foreign sources. The model finds that switching from bilateral to diagonal cumulation relaxes the restrictiveness of the ROO and leads the least productive exporters to stop exporting.     

The asymptotic expansion of the regular discretization error of Itô integrals

We study an Edgeworth‐type refinement of the central limit theorem for the discretization error of Itô integrals. Toward this end, we introduce a new approach, based on the anticipating Itô formula. This alternative technique allows us to compute explicitly the terms of the corresponding expansion formula. Two applications to finance are given; the asymptotics of discrete hedging error under the Black–Scholes model and the difference between continuously and discretely monitored variance swap payoffs under stochastic volatility models.