Predicting credit card delinquencies: An application of deep neural networks

The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real-life credit card data linked to 711,397 credit card holders from a large bank in Brazil, this study develops a deep neural network to evaluate the risk of credit card delinquency based on the client's personal characteristics and the spending behaviours. Compared with machine-learning algorithms of logistic regression, naive Bayes, traditional artificial neural networks, and decision trees, deep neural networks have a better overall predictive performance with the highest F scores and area under the receiver operating characteristic curve. The successful application of deep learning implies that artificial intelligence has great potential to support and automate credit risk assessment for financial institutions and credit bureaus.     

Litigation risk: Measurement and impact on M&A transaction terms

The purpose of the paper is to propose an original proprietary proxy of a firm's litigation risk. We extend the scope of litigation risk outside of the conflicts with shareholders and the domain of security litigation. We demonstrate that the source of the risk of litigation can be found in the firm's policies and in its management's operational or strategic decisions, even if a sector conditioning effect exists. Based on a sample of 465 US M&A transactions between 2000 and 2014, we provide evidence that the level of litigation risk, at the acquirer's level, has a positive and significant impact on the takeover premium. We also provide evidence that a significant relationship exists between the acquirer's litigation risk and the means of payment. An extension of the sample to international transactions is used as a robustness check; it confirms the previous results.     

The innovative bureaucrat: evidence from the correctional authorities in Washington State

Bureaucracies are usually regarded as inefficient, wasteful mechanisms. Contrary to this deeply rooted perception of bureaucracy, this paper documents the case of the correctional authorities in Washington State, a bureaucracy that acted with a considerable degree of innovation and professionalism. Their task was to administer a risk assessment instrument that measured the level of risk posed by offenders by way of a numerical score. They used that score to identify the level of supervision offenders were to receive once released into the community. In analyzing the data, I discovered an unusual application of the instrument that resulted in many offenders being bumped to a higher supervision level. Using a regression discontinuity design, I uncover the mechanics of the bumping-up process and I generate an instrument that is cleansed of the manipulation. I find that the manipulated instrument predicts serious recidivism events better than the cleansed instrument, especially when these events involve high-risk offenders, thus providing evidence that the authorities had good reason to undertake the manipulation.     

Central bank disclosure as a macroprudential tool for financial stability

The Basel Capital Accord (pillar 3) states that disclosure of information (transparency) is essential to financial stability. This study analyzes, through inflation reports, the disclosure of information from the Central Bank of Brazil concerning the credit market. We consider credit risk and capital buffers as measures of financial stability in this analysis. Furthermore, in order to measure the perception of the monetary authority on the credit market, we built two indices based on the central bank’s communication on credit development. We performed a panel data analysis based on a sample of 125 banks for the period from June 1999 to September 2014 (7000 observations). The findings suggest that central bank communication regarding expectations concerning the credit market contributes to financial stability. Therefore, this kind of communication of central banks (about credit development) may constitute an important macroprudential tool to improve financial stability.     

延迟退休年龄下隔代抚育与劳动参与的抉择*——基于工资收入随机性假定的研究

隔代抚育会对延迟退休年龄政策在促进劳动力供给上产生挤出效应。为了对此进行验证，本文在工资收入随机性的假定及延迟退休5年的情景下，模拟了面临孙辈照护需求的女性临近退休者提前退休所产生的福利变化。进一步，本文采用CHIP和CHARLS的微观调查数据，对不同群组的收入增长率和收入风险进行了估计，继而分析了当面临孙辈照护需求时这些收入特征对退休决策者制度退休和退休后劳动参与抉择产生的影响。总体上，在延迟退休年龄政策下，隔代抚育将对女性劳动力供给产生挤出效应。当面临孙辈照护需求时，女性临近退休者的制度退休抉择主要受自身收入增长率和收入风险的影响，收入增长率越低，或收入风险越高，她们提前退休的意愿就越强烈；制度退休后的劳动参与则更多地受子女收入增长率的影响，子女收入增长率越高，劳动参与的概率越低。     

Political uncertainty,risk of Frexit and European sovereign spreads

Using data from a prediction market (crowd-based forecasts), we build a daily measure capturing the risk of Frexit related to the 2017 French presidential elections. We study how unexpected changes in this new measure of political uncertainty in France affect European sovereign spreads vis-à-vis Germany. We show that our uncertainty proxy drives not only the French sovereign spread but also the spreads of those EU countries deemed the most vulnerable to the risk of desegregation of the Euro Zone. These results suggest that specific political uncertainty affects short-term investor’s expectations and may outweigh other economic determinants of sovereign spreads shortly prior to high stake elections     

Convex risk measures for the aggregation of multiple information sources and applications in insurance

We propose a novel class of convex risk measures, based on the concept of the Fréchet mean, designed in order to handle uncertainty which arises from multiple information sources regarding the risk factors of interest. The proposed risk measures robustly characterize the exposure of the firm, by filtering out appropriately the partial information available in individual sources into an aggregate model for the risk factors of interest. Importantly, the proposed risks can be expressed in closed analytic forms allowing for interesting qualitative interpretations as well as comparative statics and thus facilitate their use in the everyday risk management process of the insurance firms. The potential use of the proposed risk measures in insurance is illustrated by two concrete applications, capital risk allocation and premia calculation under uncertainty.     

Do hedge funds time market tail risk? Evidence from option-implied tail risk

This paper focuses on an unexplored dimension of fund managers’ timing ability: Market-wide tail risk implied by information in options markets. Constructing the option-implied tail risk, we investigate whether hedge fund managers can strategically time the tail risk through adjusting their exposure to changes of it. Using an extensive sample of equity-oriented hedge funds, we find strong evidence of tail risk timing ability of hedge fund managers. Furthermore, tail risk timing ability brings significant economic value to investors. Top-ranked funds outperform bottom-ranked funds by 5–7% annually after adjusting for risk factors. Our results are robust to various robustness checks.     

The signaling effects of education in the online lending market: Evidence from China

In this study, we use data from an online lending platform named Xinxindai in China to empirically study the signaling effects of education for the default risk of borrowers. Three dependent variables are created, namely, the probability of default, overdue payments and overdue amount, and probit models, count models and Tobit models are employed correspondingly. The number of universities in the “211 Project” of China at the city level is employed as the instrumental variable. The empirical evidence shows that education generally plays a strong signaling role in the identification of borrowers’ default risk in China. The negative marginal effect of education declines as borrowing times increase and as the marketization of regions deepens. This study helps to fill an important gap in the existing literature. Platforms and lenders can use educational level for reference in identifying the default risk of borrowers.     

Insolvency regimes and firms' default risk under economic uncertainty and shocks

One of the arguments often advanced for implementing a stronger insolvency and bankruptcy framework is that it enhances credit discipline among firms. Using a large cross-country firm-level dataset, we empirically test whether a stronger insolvency regime reduces firms' likelihood of defaulting on their debt. In particular, we examine whether it reduces default risk during increased economic uncertainty and various external shocks. Our results confirm that a stronger insolvency regime moderates the adverse effects of economic shocks on firms' default risk. The effects are more pronounced for firms in the top half of the size distribution. We also explore channels through which improved creditor rights influence firms' default risk, including dependence on external finance, corporate leverage, and managerial ethics. Our main results are robust to an alternative measure of default risk, inclusion of currency and sovereign debt crisis episodes, and alternative estimations.