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.     

Fancy Bitcoin and conventional financial assets: Measuring market integration based on connectedness networks

We investigate the relationship between Bitcoin and conventional financial assets from a perspective on the connectedness of asset networks. We adopt the method of measuring connectedness proposed by Diebold and Yilmaz (2009, 2012, and 2014) in a VAR system to study the dynamic interdependence between returns in Bitcoin, stocks, oil, and gold. We find that the connectedness between bitcoin and conventional assets is weak. The separation of positive and negative returns in the Bitcoin market shows the existence of an asymmetric pattern of the spillover effects between Bitcoin and conventional assets. A rolling window analysis finds that although Bitcoin prices experience a rising link to other financial assets, the magnitude is proven to be moderate. However, connectedness via negative returns is much stronger than via positive ones and exhibits a clearly increasing trend in recent periods. Our results in application are generally robust to other popular cryptocurrencies, such as ETH and Ripple. The findings presented in this paper have important implications for financial market participants, policymakers, and researchers in light of projected increases in the adoption of Bitcoin, as well as the rapid development of cryptocurrency.     

Structural holes and hedge fund return comovement: evidence from network-connected stock hedge funds in China

Using data from a new hedge fund database, we examine the impact of social networks on the return comovement of stock hedge funds in China. We use structural holes in the college alumni networks of managers to measure the managers’ social network positions. We perform an empirical analysis on a sample of 3,012 hedge fund products in China from 2010 to 2017. We find that greater structural holes are associated with higher return comovement. The positive impact of the structural holes on return comovement is not affected by market cycles, a manager's major in college, or his or her abilities.     

区域贫困程度测度研究:甘肃案例

区域贫困程度测度是精准施策,打赢脱贫攻坚战的重要依据。在对已有贫困程度测度方法回顾的基础上,文章通过分析深度贫困地区的贫困特征,提出区域贫困程度测度原则,构建区域贫困程度测度指标体系,并以甘肃为例对深度贫困县贫困程度进行测算,进一步了解深度贫困县的贫困现状、集中区域、影响因素及贫困差距等,以期为地方打赢脱贫攻坚战提供借鉴。     

Network ties and export propensity of Vietnamese small and medium enterprises

This paper investigates the impacts of different network ties on export propensity of Vietnamese small and medium enterprises (SMEs) in the manufacturing sector. Using data from a survey of over 2,600 manufacturing SMEs in 2015, we found that social networks contribute positively to the export propensity of SMEs, while the size of business networks negatively associates with the likelihood of export. However, bank networks and political networks are not significant for the propensity to export of Vietnamese SMEs. We discuss the results in detail and offer recommendations for SME owners, managers and policy makers.     

Using machine learning and big data for efficient forecasting of hotel booking cancellations

Cancellations are a key aspect of hotel revenue management because of their impact on room reservation systems. In fact, very little is known about the reasons that lead customers to cancel, or how it can be avoided. The aim of this paper is to propose a means of enabling the forecasting of hotel booking cancellations using only 13 independent variables, a reduced number in comparison with related research in the area, which in addition coincide with those that are most often requested by customers when they place a reservation. For this matter, machine-learning techniques, among other artificial neural networks optimised with genetic algorithms were applied achieving a cancellation rate of up to 98%. The proposed methodology allows us not only to know about cancellation rates, but also to identify which customer is likely to cancel. This approach would mean organisations could strengthen their action protocols regarding tourist arrivals.     

How do hospitality entrepreneurs use their social networks to access resources? Evidence from the lifecycle of small hospitality enterprises

This study investigates entrepreneurs’ use of social networks to access resources during the conception, start-up, and consolidation stages of small enterprises in the hospitality industry in Sergipe State, Brazil. This study analyzes four cases of small hotel ventures, employing cross-case analyses to identify the patterns, similarities, and differences between the cases. The study findings highlight that, in the start-up stage, entrepreneurs access fewer resources, utilizing only family and friends, primarily as moral support. In the consolidation stage, entrepreneurs rely more on their weak links, accessing them with greater frequency. Mobilizing social networks is a dynamic process, and how entrepreneurs use these networks changes throughout the business-creation process. This is one of the first studies on how entrepreneurs use their social networks, especially in a developing economy.     

强化食品抽样检验推动食品安全深度监管

做好食品抽样检验工作是确保食品质量和安全的关键,本研究对目前国内食品抽样检验管理现状进行了分析,针对食品安全抽样检验管理存在的问题提出要强化制度建设、强化技术团队建设、制定统一检测标准等方法,并提出进一步深化改革食品安全抽样检验管理办法,旨在保障公众食品安全,提高食品抽样监管力度。     

Multilayer financial networks and systemic importance: Evidence from China

In this paper, we develop a multilayer network structure and reveal the relationship between network structure and systemic risk. Unlike many previous studies, our model considers both liability and cross-holding of shares between financial institutions simultaneously. We propose a new systemic risk measurement by exploring the dynamic mechanism of financial contagion in the multilayer network. We display the network structure of Chinese financial institutions, including connectivity and diversity, and identify the systemic importance of them. We demonstrate that the multilayer network plays a non-linear role in financial risk spreading. Using the panel regression model and several experiment evidences, we show that the systemic risk can be explained more effectively by the linkage diversity more than the connectivity at both the institutional level and the system level. Our results highlight the importance of considering contagion mechanisms that go beyond a simple single-layer network structure.