Neural networks are widely used in automatic credit scoring systems with high accuracy and outstanding efficiency. However, in the absence of prior knowledge, it is difficult to determine the set of hyper-parameters, which makes its application limited in practice. This paper presents a novel framework of credit-scoring model based on neural networks trained by the optimal swarm intelligence (SI) algorithm. This framework incorporates three procedures. Step 1, pre-processing, including imputation, normalization, and reordering of the samples. Step 2, training, where SI algorithms optimize hyper-parameters of back-propagation artificial neural networks (BP-ANN) with the area under curve (AUC) as the evaluation function. Step 3, test, applying the optimized model in Step 2 to predict new samples. The results show that the framework proposed in this paper searches the hyper-parameter space efficiently and finds the optimal set of hyper parameters with appropriate time complexity, which enhances the fitting and generalization ability of BP-ANN. Compared with existing credit-scoring models, the model in this paper predicts with a higher accuracy. Additionally, the model enjoys a greater robustness, for the difference of performance between training and testing phases.
Chinese local officials have strong incentives to stimulate economic growth in the pursuit of promotion. However, the connection between promotion pressure of local officials and investment in the real estate market has not been rigorously explored. By using the panel data of local leaders (municipal party secretaries or mayors) from 2002 to 2010, this paper investigates the correlations between local leaders’ promotion pressures and growth in real estate investments. Empirical results show that local leaders’ promotion pressures are significantly and positively correlated with the growth of the real estate market. Furthermore, the positive effect of promotion pressure on real estate development is significant if the leader is young or born locally, whereas this effect is insignificant if the leader is older or not a native. Our findings provide new evidence on how local leaders may strategically intervene in local economic activities.
Cross-border venture capitals (CBVCs) are increasingly prevailing in recent decades, inter alia in emerging markets like China. The venture capital (VC) firms investing outside their home countries are faced with foreignness which is broadly regarded as liability. The primary aim of this article is to contribute to our understanding how foreignness affects VC’s strategy when entering emerging markets, particularly with respect to the foreignness originated from cultural distance. The data consist of over 5,000 CBVC deals taking place in China mainland from 1988 to 2016. Our empirical study shows that, with foreignness growing, it turns from liability into advantage in the context of CBVCs. We find an inverse U-shape relationship between foreignness and syndication, with VC firm’s reputation as the moderator. Besides, foreign VC firms establish local subsidiary when faced with foreignness, which serves as alternative to syndication. The key contribution of this article is that foreignness turns from liability into advantage in emerging markets, which exerts a curvilinear impact on the entry strategy of VC firms. This study advances the knowledge of foreignness and VC strategy, and sheds new light on entrepreneurial activities in emerging markets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.