Yibing Chen

Credit card customer analysis based on panel data clustering

Abstract In this paper, we propose a new distance measurement which can be used in panel data clustering. The distance as we designed can be calculated with weight and without weight. If users put more attention on recent data, a heavier weight can be assigned to the recent data. We use real panel data of a commercial bank’s credit card to examine the performance of our new distance measurement. The results show that our distance measurement can reflect the information of different periods and panel data can be used to cluster to find new knowledge. This study discovers different knowledge structure from the traditional econometrics analysis with the help of data mining algorithms.

Based on Information Fusion Technique with Data Mining in the Application of Finance Early-Warning

Abstract Data mining has been widely applied to make prediction for finance crisis risk, and they often obtain a good result. Financial distress prediction can be formulated as a classification problem using data mining. Many data mining methods for classification can be used to solve the finance early-warning problem, however, “one time” data mining process cannot often obtain a well support decision, and one single method has its weakness for classification. In this paper, we use information fusion technique to build a finance early-warning model based on data mining methods, which can integrate the respective strengths from different data mining methods to improve the prediction accuracy rate, it fuses the different data mining results to gain the prediction results for reliable decision. We also choose the real dataset of Chinese listed manufacturing companies to predict the finance risk with information fusion technique based on SVM and Logistic model, and make comparison with the two methods to make prediction respectively.

Domestic Systemically Important Banks: A Quantitative Analysis for the Chinese Banking System

This paper serves as a response to the official assessment approach proposed by Basel Committee to identify domestic systemically important banks (D-SIBs) in China. Our analysis presents not only current levels of domestic systemic importance of individual banks but also the changes. We also consider the systemic risk of the whole banking system, by investigating how D-SIBs and non-D-SIBs are correlated before and after the recent financial crises using Copula. We find that the systemic importance of major banks is decreasing, while some banks becoming more systemically important should require tight regulations. D-SIBs as a whole subsystem display stronger correlation with non-D-SIBs than the individual D-SIBs, which alerts the regulatory to pay attention to “too-many-to-fail” problems. Contagion effects between D-SIBs and non-D-SIBs exist during the subprime crisis, but did not exist during the European debt crisis. This yields good signal of a more balanced banking system in China.

Sectoral Diversification and the Banks’ Return and Risk: Evidence from Chinese Listed Commercial Banks

Abstract This paper investigates the effects of sectoral diversification on the Chinese banks’ return and risk using panel data on 16 Chinese listed commercial banks during the 2007-2011 period. We construct another new diversification measure, taking systematic risk of different sectors into consideration by weighting them with their betas and compare the results with those of more conventional measure HHI. We find that sectoral diversification is associated with reduced return and also decreased risk at the same time, which however, contradicts existing findings in developed countries and also in emerging economies.

Domain Knowledge Based Personalized Recommendation Model and Its Application in Cross-selling

Abstract This paper proposes a new personalized recommendation model based on domain knowledge to emphasize the importance of domain knowledge in recommendation process. We focus on integration of domain knowledge in the whole process of personalized recommendation to overcome those problems such as poor scalability, poor in dealing with data sparseness, overlooking the factor of profit when using traditional collaborative filtering as recommendation method. We apply our new method in enterprises cross-selling as a case study at the last part of this paper.

Domain Driven Two-Phase Feature Selection Method Based on Bhattacharyya Distance and Kernel Distance Measurements

This paper proposes a two-phase feature selection method specific for bioinformatics domain from classification perspective in data mining. In the first phase, Bhattacharyya distance measurement is used for filtering the majority of irrelevant genes. Upon the basis, we apply floating sequential search method (FSSM) to further select informative gene set using kernel distance as measurement of class separability. The verification of colon tissue dataset using support vector machines (SVMs) proves that informative gene set selected by our method is acceptable for disease identification.

How does credit portfolio diversification affect banks’ return and risk? Evidence from Chinese listed commercial banks

AbstractDoes diversification of credit portfolio indeed lead to increased performance and reduced risk of banks as traditional portfolio theory suggests? This paper investigates empirically the effects of diversification on the Chinese banks’ return and risk from the aspect of sector. Panel data on 16 Chinese listed commercial banks during the 2007–2011 period is used for the study. We construct a new diversification measure, taking systematic risk of different sectors into consideration by weighting them with their betas and compare the results with those of more conventional measure HHI. We find that sectorial diversification is associated with reduced return and also decreased risk at the same time, which however, contradicts existing findings in developed countries such as Italy and Germany, and also in emerging economies such as Brazil and Argentina. Our analysis also provides important implication for regulators and policy makers of the banks in emerging markets.

A New Measurement of Sectoral Concentration of Credit Portfolios

Abstract In this paper, we construct a new measurement of sectoral concentration of credit portfolios--risk-adjusted HHI. This measurement takes systematic risk of different sectors into consideration by weighting them with their betas. This paper investigates the effects of sectoral concentration on the Chinese banks’ risk using panel data on 16 Chinese listed commercial banks during the 2007-2011 period and compares the results of the new measurement with those of more conventional measure HHI. We find that sectoral concentration is associated with higher risk, and our new measurement performs well to capture the change of systematic risk of sectors and exposures to sectors at the same time. Our analysis may provide important implication for regulators and policy makers of the banks in developing markets.

Context-based knowledge discovery and its application

Mankind is inundated by information, but thirst for knowledge. The use of knowledge discovery to identify potentially useful knowledge from massive data has become an important method, which increasingly attracts much attention. In order to solve the problem of too much emphasis on the accuracy of the algorithm while ignoring the context of the application of knowledge existing in traditional knowledge discovery, we proposed theoretical framework of context-based knowledge discovery. Through the study of context representation based on probability distribution and calculation of context variance and distance etc, data selection based on similarity assessment of context is achieved. Further a context-based KNN classification algorithm is designed. Finally the validity of context-based knowledge discovery is verified.

Pension Fund Asset Allocation: A Mean-Variance Model with CVaR Constraints

Abstract In this paper, we first review some important aspects of asset allocation for some typical large Social Security Reserve Funds (SSRFs) in the world. Then we present the mean-variance model with CVaR constraints as asset allocation methodology. Concerning the real circumstance in China, we apply the model to pension fund asset allocation. The empirical results show that to maintain purchase power of pension fund, certain proportion should be invested in stocks as well as direct equity investments. We also find that time horizon significantly influence asset allocation of pension fund. If time horizon is longer, more allocations to stocks and equity investments help the pension fund to achieve better performance.