Band 2, Heft 6

In order to improve the forecasting accuracy, a hybrid error-correction approach by integrating support vector machine (SVM), empirical mode decomposition (EMD) and the improved cuckoo search algorithm (ICS) was introduced in this study. By using two indexes as examples, the empirical study shows our proposed approach by means of synchronously predict the prediction error which used to correct the preliminary predicted values has better prediction precision than other five competing approaches, furthermore, the improved strategies for cuckoo search algorithm has better performance than other three evolutionary algorithms in parameters selection.

A particle filter based method to price American option under partial observation framework is introduced. Assuming the underlying price process is driven by unobservable latent factors, the pricing methodology should contain inference on latent factors in addition to the original least-squares Monte Carlo approach of Longstaff and Schwartz. Sequential Monte Carlo is a widely applied technique to provide such inference. Applications on stochastic volatility models has been introduced by Rambharat, who assume that volatility is a latent stochastic process, and capture information about it using particle filter based “summary vectors”. This paper investigates this particle filter based pricing methodology, with an extension to a stochastic volatility jump model, stochastic volatility correlated jump model (SVCJ), and auxiliary particle filter (APF) introduced first by Pitt and Shephard. In the APF algorithm of SVCJ model, it also provides a modification version to enhance the performance in the resampling step. A detailed implementation and numerical examples of the algorithm are provided. The algorithm is also applied to empirical data.

This paper discusses multi-period stochastic cash balance problem with fixed costs when the decision maker is risk averse. By using the consumption model introduced by Chen et al, we characterize the structure of the optimal policy for the stochastic cash balance problem under the general increasing concave utility function and exponential utility function, respectively. We show that the structure of the optimal policy for a decision maker with exponential utility function is almost identical to the structure of the optimal risk-neutral operations policy. Furthermore, we extend the results for the exponential utility function to the ambiguity aversion case.

With the rapid development of mobile internet and the continuous replacement of new smart phones, the advancement of we-media age, and advent of the era of 4G, reading revolution has opened. This paper is to study which factors affect users’ continuance intention. We discussed the relationship between experience involvement, subjective norms, and the dimensions of perceived value as well as users’ continuance intention. The results show that the model which this paper put forward could effectively explain the hypothesizes, and this paper mainly draws the following conclusions: subjective norm significantly affect experience involvement; on one hand, experience involvement significantly and directly affect users’ continuance intention, and on the other hand, indirectly affect users’ continuance intention by significantly affect the users’ perceived usefulness, perceived pleasure and perceived cost; experience involvement can’t significantly affect users’ perceived image enhancement. We suggest the mobile reading providers pay more attention to the free experience process, increasing its convenience, enriching its content and rationalizing its cost. And they should also optimize the mobile reading to improve users’ perceived image enhancement. Mobile reading providers should let users more involved to achieve value co-creation.

The GM(1, N ) model is a very important prediction model of the grey system. But the inherent defect of GM(1, N ), which may cause very large error, is still there. This paper analyzes the source of the error of GM(1, N ) and reveals that it’s all the back ground values that effect the precision and applicability of GM(1, N ). Three methods are employed to revise the GM(1, N ) model. The simulation test shows the new models perform with higher precision and robustness. Even in some extreme cases, in which the original GM(1, N ) is invalid, the new models are still valid and perform well.

In this paper, we deal with the Nash differential games of stochastic singular systems governed by Itô-type equation in finite-time horizon and infinite-time horizon, respectively. Firstly, the Nash differential game problem of stochastic singular systems in finite time horizon is formulated. By applying the results of stochastic optimal control problem, the existence condition of the Nash strategy is presented by means of a set of cross-coupled Riccati differential equations. Similarly, under the assumption of the admissibility of the stochastic singular systems, the existence condition of the Nash strategy in infinite-time horizon is presented by means of a set of cross-coupled Riccati algebraic equations. The results show that the strategies of each players interact.

This paper develops a overall unbalanced multiplicative linguistic evaluation scale. Based on the developed linguistic evaluation scale and linguistic weighted averaging (LWA) operator, the technological innovation management ability of five food enterprises is evaluated. Numerical results verified the validity and utility of the scale. Meanwhile, it indicates that to improve the level of technological innovation, an enterprise should make more efforts to stimulate innovations by using the enterprises distribution system, to cultivate the leader and the staff’s positive attitude to an innovation failure, to thoroughly analyze the reason of the termination of an innovation project and to strengthen the leader and the staff’s innovation awareness. The overall unbalanced multiplicative linguistic evaluation scale can also be extensively applied to other fields such as project evaluation, engineering management, medical diagnosis and personnel appraisal.

By comparing several kinds of continuous functions, a normal distribution function-based model is proposed to improve the existing Levy policy of dividend tax in this paper. The improved model is adopted to stimulate the long-term investment and contain the short-term speculation. Further, this improved model paves an avenue to overcome the deficiency on the double policy of dividend tax rate by holding stock period with one day difference and also adjust the tax revenues by controlling the parameters of the distribution function. The findings from this study suggest that the improved model with normal distribution function may provide more reasonable results based on the data from the stock market and, finally, the proper decision is discussed.