Table of Content

28 January 2015, Volume 24 Issue 1    Next Issue

Select

Topic Identification and Visualization for Open Team Innovation 2015, 24 (1):  1-7.  doi: C 931.6 Abstract ( )   The global innovation landscape is changing open innovations. In open innovative team, electronic argumentation based on Web is becoming one of the most primary and important innovative activities. It is very important to mine, identify and visualize the argumentation topic of mass argumentation information in the process of open team innovation. These benefit not only mastering the whole team progress and the latest development rapidly and accurately, but also recommending appropriate knowledge and field experts to team members according to their argumentation topics. In order to strike on the main problems of classic text topic mining, an automatic topic identification method is studied and proposed in this paper. A semantic computing method based on argumentation ontology and argumentation tree structure is proposed and built during documentation modeling phase. AntSA algorithm is employed for short-text clustering during topic mining phase. The contribution ratio of the nouns in each category node to argumentation topics is proposed and computed to identify topics of each category. Consequently, the visualization system of topic identification for open team innovation argumentation is designed and development based on the proposed method. The visualization system is able to automatically identify and intuitively exhibit semantic relationships and structural relationships between various argumentation topics. Experiment study of topic identification method for open team innovation argumentation is conducted as well. References | Related Articles

Select

Searching Cost, Network Externalities and Price Dispersion: Evidences from Online Clothing and Computer Accessories Markets in Taobao 2015, 24 (1):  8-13.  doi: L 15；L 20；L 86 Abstract ( )   This paper studies the effect of Searching Cost, and Network Externalities on Price Dispersion using the data from Online Clothing and Computer Accessories Markets in Taobao. The traditional Bertrand model ascertain that when there are more retailers, they would tend to fix the price at the marginal cost. As a result, the price dispersion of the product is zero. However, with the emergence of the online market, many scholars have found that when there are more retailers, the price dispersion will become higher. The results of this study shows that there is a threshold point where the number of retailers influences price dispersion in C2C online market such as Taobao. Before this critical point, the more retailers, the higher of the price dispersion. However, once surpass this critical point, the more retailers, the lower of the price dispersion. For different kinds of products, the threshold number is different. References | Related Articles

Select

On the Feedback Mechanism of Performance Accountability for Higher Education Institutions based on TOPDIS Method 2015, 24 (1):  14-21.  doi: G 647；F 812.2 Abstract ( )   The main purpose of performance accountability for higher education institutions is not only to make universities and education authorities know their performance on efficiency of resource utilization and education quality, but also to make them fully understand their own problems about the allocation of educational resources and performance management and promote them to adopt appropriate measures to make better use of available resources and improve the teaching quality. In this paper, we take the education authority as the accountability subject and choose university A that operates directly under the Ministry of Education as accountability object. Assuming constant educational resource input level of higher education institutions, we use the method of TOPDIS（technique for order preference by distance to ideal solution）to analyze the advancements, difficulties and potentials for improvement of the output performance indicators for university A. In order to set up a communication and feedback mechanism between accountability subject and object, we put forward some management suggestions for university A from the perspective of the education authority. References | Related Articles

Select

Passengers’ Transfer Behavior-based Urban Transport Flow Distribution and its Applications 2015, 24 (1):  22-37.  doi: U 491 Abstract ( )   Nowadays, the work and life mode of “living outside the city, working in the downtown” is very common in big cities in China. Thus the residents' travel distance is extended, so does the radius of public transportation and transfer is inevitable. According to the practical needs, combined with the particularity of transit network, the generalized bus route is defined to better depict the passengers’ route choice behavior. Passengers’ travel behavior in line with Markov decision process is analyzed and studied. The state-action space and the state transition probability involved in the process of transit travel are presented, an unbalanced public transit assignment model based on Markov chain is developed, and the corresponding algorithm is developed. An application example is presented with real data from Chengdu bus system to verify the model and the algorithm. Sensitivity analysis is presented as well based on the results of the transit assignment. References | Related Articles

Select

Modeling and Applications of Traveler Destination Choice Behavior based on Bayesian Network 2015, 24 (1):  32-37.  doi: U 491.1 Abstract ( )   This paper presents a Bayesian method for travel destination choice of urban residents. We develop a Bayesian approach for learning Bayesian networks from a combination of prior knowledge and statistical data, which is derived from an inhabitant trip survey in Jilin, China. We expound a methodology for assessing informative priors needed for Bayesian network learning. We studies structure learning of Bayesian networks for knowledge discovery and decision supporting system. The Decision Tree Algorithm is used to discrete the continuous attributes in database of the destination choices. Bayesian network model in the travel decision supporting system is obtained by K2 algorithm, which draw a Directed Acyclic Graph (DAG) that can express the relationship between several nodes. We conduct a case study on inhabitant destination choice with Bayesian methods based on discrete decision model. We calibrate the model and design simulation process of destination choice for the residents to explain the many factors which affect the destination choice decision. We also use Bayesian networks to analyze how many factors can affect the destination choice decision, and the relationship between the factors. We then describe a methodology for evaluating Bayesian network learning algorithm, and compare this approach with various approaches. We analyze the prediction results which have a higher prediction accuracy from the disaggregate level. The paper provides a new method to simulate the travel destination choice of inhabitants which can help us to learn the transport mechanism of travel behavior and to make some developments of transport policy. References | Related Articles

Select

Collaborative Transportation Route Optimization with Lower Bound Flows 2015, 24 (1):  38-42.  doi: N 94；O 22 Abstract ( )   This paper studies collaborative transportation route optimization with lower bound flows (CTROLBF). CTROLBF allows all O-D (origin-destination) flows reaching the destination optionally passing through 0, 1 or 2 hubs within a limited routing distance, while the number of flows on hub arcs are larger than a giver number, and seeks the optimal way of transportation routing of all O-D flows to minimize the total costs. CTROLBF arises airline transportation, road transportation and postal services. We build a linear programming model and provide a heuristic algorithm based on Dantzig-Wolfe decomposition. The computational experiments show the algorithm works well. We also apply the algorithm to Chinese hub-and-spoke airline network with lower bound flows on hub airlines. References | Related Articles

Select

Flexible Flow Shops Scheduling for Order Fulfillment 2015, 24 (1):  43-47.  doi: O 223 Abstract ( )   Production scheduling for order fulfillment is practical in most manufactories. We study the flexible flow shop scheduling for order fulfillment, and take consideration of the order attribute of jobs. The objective is to minimize the weighted tardiness of all orders. We proposes an algorithm to optimize the schedule. References | Related Articles

Select

Financial Crisis Prediction based on Biorthogonal Wavelet Hybrid Kernel KPCA-SVM Model 2015, 24 (1):  48-55.  doi: F 276. 6 Abstract ( )   Financial crisis prediction is generally studied using the kernel principal component analysis (KPCA) and support vector machine (SVM) model. However, the kernel function used in these methods is basically single kernel function. Actually, hybrid kernel is superior to the component kernels in dealing with non-linear issues, for it can make full use of their different feature mapping abilities. In view of the excellent performance of biorthogonal wavelet in nonlinear signal processing, a new type of biorthogonal wavelet kernel function is constructed and shown to be valid due to the satisfaction of the admissibility conditions of the positive definite kernel. In addition, biorthogonal wavelet hybrid kernel function is constructed and KPCA-SVM model for financial crisis prediction based on biorthogonal wavelet hybrid kernel function is also proposed. The empirical study on the listed companies in China's securities market is conducted. The results show that the biorthogonal wavelet hybrid kernel function constructed can effectively improve the feature extraction performance in KPCA and enhance the prediction accuracy of SVM model to a great degree, hence the accuracy of the financial crisis prediction is thus significantly improved. References | Related Articles

Select

Loan pricing based on correlation between default probability and Loss-Given-Default 2015, 24 (1):  56-62.  doi: F 830 Abstract ( )   Based on the asymptotic single factor model, we introduce the positive correlation between defaults and losses, and propose an approach for measuring the credit risk of economic capital, which can be applied to any underlying distribution for the Loss-Given-Default (LGD). We then propose a method of estimating the spread on the credit risk-adjusted interest rates and derive the target price formula by using risk-adjusted performance indicator RAROC. Numerical examples are provided to demonstrate that the assumption of constant LGD underestimates the interest of bank loan, and the difference of the interest according to constant LGD and according to the stochastic LGD increases with growing probability of default. References | Related Articles

Select

Common Volatility Spillover of Financial Risk based on Spectral Clustering-ICA-Granger Model 2015, 24 (1):  63-70.  doi: F 830.9 Abstract ( )   n this paper common volatility spillover among the main countries is analyzed by the spectral clustering-independent component analysis-Granger Model. First, we use GARCH model to describe the volatility of the main countries, and the spectral clustering method to partition the volatility data sets. We then use the independent component analysis and Granger causality test to analyze spillover among the main counties in different periods. The results show that the proposed model can effectively describe the common volatility spillover of the three financial crisis. References | Related Articles

Select

Study on the Relationship between Structure and Resilience of Chinese Stock Correlation Network 2015, 24 (1):  71-77.  doi: F 830 Abstract ( )   Utilizing the closing prices of A shares in Shanghai and Shenzhen stock market from 2002 to 2012, we establish the dynamic weighted stock correlation networks from the perspective of complex network, and analyze the topology structures, resilience and its influencing factors. The empirical results demonstrate that the topology structures are highly linearly correlated. The higher the average price fluctuation correlation among the stocks, the smaller and highly clustered are the networks. The topology structures and market trends have strong relationships. The clustering coefficient and stock returns are positively correlated with resilience, and the node entropy and stock return volatility are negatively correlated with resilience. The results demonstrate the price fluctuation rules among stocks, and they are good guides for portfolios and risk management in stock markets. References | Related Articles

Select

A Portfolio Selection Model with Random Fuzzy Returns and Weighted Max-Min Operator and Its Empirical Study 2015, 24 (1):  78-84.  doi: F 832.0；F 224.9 Abstract ( )   For the uncertainty in the stock market, we model the security returns as random fuzzy variables, and build the expected return and target probability membership functions according to investors’ psychological trait and based on the prospect theory. Considering investors’ diversified requirements of expected return and target probability, we construct a weighted max-min random fuzzy portfolio model by using weighted max-min operator and obtain the optimal solution. We also empirically study the performance of the proposed model. The result shows that: the efficient frontier of the model is inconsistent with mean-variance model; by changing the target weights of expected return and target probability, the model can be used to construct portfolios to meet different investors’ psychological requirement; the investment return of the model outperforms mean-variance model. References | Related Articles