This article studies a volatility forecasting model based on volatility measurement error, and extends it with nonlinear time series model, expecting to improve the forecasting performance. According to the literature, volatility series may have both long memory and nonlinear characteristics. Heterogeneous autoregressive (HAR) model has long memory characteristic. Adjusting HAR model with measurement error promotes model persistence. Further combine the model with time-varying parameter model which is nonlinear, so that structure change and reduction of heteroscedasticity are achieved. Realized range-based volatility is computed based on high-frequency data of CSI300 (2652 trading days) to test the effect of the models. Among the fixed parameter models, the out-of-sample forecasting performance is significantly improved by adding measurement error as adjustment variable. Among the time-varying parameter models, most of the models with measurement error dominate their corresponding models without measurement error. The predictions of time-varying parameter models are in general significantly better than their counterparts with fixed parameters, especially when the prediction period is long.
Through decomposing the volatility of underlying asset into two uncorrelated components, this article constructs a new option pricing model and resolves the option price formula. After analyzing skewness and kurtosis of underlying asset return, and studying implied volatility of option under the new model, this work calibrates model parameters using the market data. The result of study shows that new model can be suitable for volatility components with different evolution processes, it can generate substantial degree of excess kurtosis and depth of volatility smile even for options with short maturity, and it has more pricing effectiveness by introducing new risk factor.
This paper studies an optimal portfolio selection problem in a defined contribution pension plan during the decumulation phase. The pensioner withdraws an amount for daily-life consumption from the pension fund periodically, and then invests the remaining wealth in a risk-free asset, a stock and an inflation-index bond available in the financial market until the time of compulsory annuitization. The pensioner aims to find the optimal investment strategy to minimize the accumulative expected deviations of the running wealth from the targets, which are measured by the quadratic loss functions. The closed-form expressions for the targets without the penalty of surplus, the optimal investment strategy, the optimal value function, the bankruptcy probability and the distribution of the distance between the terminal wealth and the target are obtained by using the methods of dynamic programming and stochastic control. Finally, mathematical analysis and numerical simulation are presented to study the property of the target at each time, to investigate the effects of the terminal target and withdrawn amount on the bankruptcy probability and to illustrate the effects of the appreciation rate and volatility rate of the inflation on the deviation of the running wealth from the target, the expected wealth at each time and the bankruptcy probability.
In the process of multi-period portfolio selection, the frequent adjustment of investment proportion will produce a series of transaction costs, which is an important factor affecting the decision-making of investment. Online portfolio belongs to the multi-period portfolio; the proportion of investment needs to be adjusted in accordance with the investment stage, rather than a one-time determination. This paper introduces the transaction costs into the online portfolio model, and further applies the weak aggregating algorithm to integrated finite expert advice to design online portfolio strategy. Firstly, this paper discusses the situation that expert advice is fixedly investing on single stock at every period and obtains the single aggregating strategy with transaction costs; and proves the conclusion that comparing with best expert, there exists asymptotical lower bound on the difference between their average cumulative gains. Secondly, this paper discusses the situation that the expert advice is fixedly investing on different numbers of stocks at every period, and obtains the mixed aggregating strategy with transaction costs, and provides the competitive performance of this strategy. Based on the transaction data of New York stock market, numerical examples are given to prove that the single aggregating strategy and mixed aggregating strategy with transaction costs can achieve almost the same performance as the best expert advice, and the effect of transaction costs on strategies' performance is also analyzed.
Under the framework of Ponzi schemes, the competition decision model of the new financial platform which is based on the obfuscation strategy is established to analyze the process of risk accumulation and risk evolution. By the game theory, this paper studies the optimal obfuscation strategy of heterogeneous platform under competition. Furthermore, we empirically analyze the impact of the key parameters on platform funds by numerical simulation. The conclusion shows that the platform with the high promised rate usually chooses high obfuscation strategy, and the platform with low promised rate will choose the obfuscation strategy according to the advantage. High promised rate and high financial leverage ratio increase the risk of the platform. If the platform is fine, high obfuscation strategy will make the platform increase revenue and accelerate the accumulation of capital. High obfuscation strategy can extend the survival time of platform when the platform is fragile, but it can't reverse the survival trend. If the platform can make an automatic recovery, high obfuscation strategy will make the period of the crisis longer.
After the successful conclusion of Paris Climate Conference (COP21), countries are now attempting to identify implementation measures to address climate issues. In order to achieve the 2-degress target, human needs to make more efforts on mitigation measures to control atmospheric carbon concentration under 450 ppmv. Due to the different levels of economic development, countries, even for the different regions in China, have different local development pathways of low carbon technologies. Therefore, it is of great significance to study the evolution of economic development and energy technologies in multi-regions by establishing multi-region integrated assessment model (IAM). This article extends the WITCH model to a Global-Chinese multi-regional IAM model, named as WITCH-China, to study the evolution of Chinese multi-regional economic development, energy consumption and low-carbon energy technology development. This may provide useful insights for scholars and policy designers to forecast the future consumption pathways of low-carbon technologies of different regions in China, and contribute to the creation of strategic development plans related to the diffusion of carbon-free technologies throughout the world and China.
The industrial added value is an important indicator of the effectiveness of the real economy. With the increase of the uncertainty of China's economic development, more timely forecast of its growth is particularly important. In this paper, firstly an advanced mixed frequency structure vector autoregression model is established; then the mathematical expressions are derived for the prediction of industrial added value and the forward rolling prediction is given. And the prediction model is transformed into state space structure, and Bootstrap importance sampling step is used to test the robustness of the model. Based on the monthly data from January 1996 to March 2016, the empirical research shows that the prediction model is reasonable, and the parameter estimation is convergent and robust. In addition to the impact of its own inertia of the industrial added value, the 1~2 lags monetary policy M2 and consumer spending have some positive impact on the half-month frequency in the industrial added value growth rate. The full sample prediction, partial sample prediction and predictive extrapolation are reasonable and feasible, and the high frequency half-month forecast is an effective early warning to growth fluctuations of the industrial added value. Finally, relevant policy implications and prospects are put forward.
Intelligent regional aggregator (IRA) integrates regional electric vehicles (EVs) to participate in electric power market transaction. However, in the pool market (include the day-ahead and real-time markets), the transaction risk of IRA will be increased by the randomness of pool market price. To this end, the bidding strategy model of IRA aims to minimize the conditional expectation of electricity purchase cost in pool market with considering the pool market price uncertainty. And the model is reformulated to be a stochastic optimization problem with the conditional value-at-risk (CVaR) constraints. The integration function with probability density of random variable is difficult to solve, so the Monte-Carlo simulation method is adopted for prediction of the distribution characteristics of the pool market price. And the model is transformed and discretized by sample average approximation as a solvable convex programming problem. Numerical experiments show that the IRA controls EVs bidding in the pool electricity market, and manages EVs charging profile to achieve the purposes of low peak valley difference and enhance stability of power grid.
Quality positioning strategy is the determinant of store brands success. Under the condition of cost difference between store brands and national brands, we consider the introduction strategies and channel effects of the store brands whose quality positioning strategies are different. The results are showed as follow:(i) When the wholesale price of the low-quality national brand is high enough, the retailer can introduce the economic store brand. When the wholesale price of the high-quality national brand is high enough, the retailer can introduce the premium store brand. (ii) No matter which kind of store brand the retailer introduces, the wholesale price and retailing price of the national brands will decrease, but their decreased degrees decrease with the store brand cost advantage of decreasing. When the economic store brand is introduced, the decreased degrees of the wholesale price and retailing price of the national brands increase with the the store brand quality increasing. When the premium store brand is introduced, the decreased degrees of the wholesale price and retailing price of the national brands decrease with the store brand quality increasing. (iii) No matter which kind of store brand the retailer introduces, the profits of the national brands will decrease, and their decreased degrees decrease with the store brand cost advantage decreasing. (iv) No matter which kind of store brand the retailer introduces, the retailer's profits will increase. When the economic or premium store brand is introduced, the increased degrees of retailer's profits increase, with the store brand cost advantage decreasing or the store brand quality increasing. In these three kinds of store brands being discussed, the premium store brand could most significantly enhance the retailer's profits. More importantly, the introduction of any kind of store brand could improve the profits of the entire supply chain.
Focusing on an express company proving shipping service for perishable products, this paper considers the shipping freshness requirement of products and researches this company's shipment consolidation policy. Firstly, this paper employs the quantity-based policy combining the perishable characteristic of products and formulates a shipment consolidation model by applying the stochastic renewal theory to decide the shipment quantity with the objective of minimizing the average expected total cost. Then, by analyzing this model, this paper shows:1) the internal changing law of the average expected shipment cost and the average expected shipment consolidation penalty cost; 2) the internal changing law of the average expected total cost with respected to the shipment consolidation quantity; 3) whether the company applies the shipment consolidation policy hinges on demand rate, fixed shipment cost and unit shipment consolidation penalty cost and 4) the optimal shipment consolidation quantity depends on the combination of demand environment, cost environment and product environment. Based on the analyzing results, an algorithm is developed. By conducting some numerical experiments, this paper obtains the relationship of the optimal shipment consolidation quantity, the optimal unit inputting freshness-keeping cost and the expected shipping consolidation cost per product with the demand environment, the cost environment and the product environment faced by company, respectively. All conclusions in this paper are helpful to express companies that provide the delivery and distribution service of perishable products.
The joint emergency supplies reserves of governments and enterprises can effectively improve the dilemma that supplies are stored too more or too less by governments only. Realizing the joint reserves through market-oriented contracts can overcome the disadvantages of administrative means. Based on these, this paper constructs the model of joint emergency supplies reserves of governments and enterprises based on option procurement. After gaining the optimal decisions of the government and enterprise, the paper gives the condition that the enterprise can participate in the joint reserves and derive the scope of the parameters of option contract that the joint reserves can improve the total reserves of supplies and reduce the level of the government's inventory compared with the model of governments reserving alone under the different situation of spot markets. Meanwhile, the paper also gives the condition that the supply chain can be coordinated and the government and enterprise achieve the win-win situation. Finally, all conclusions above are validated by numerical examples. We further analyze the impact of the uncertainty of the demand of supplies on two reserve models and derive the conclusion that the advantages of joint reserves are more prominent with the uncertainty of the demand of supplies increasing compared with the government reserving alone.
When evidence theory is applied to emergency decision-making, it is often supposed that the information sources are independent which is contrary to the reality. Therefore, we propose the method for multi-attribute emergency decision-making considering the interdependence between information sources. Firstly, the multi-attribute emergency decision-making problem is represented based on evidence theory. Secondly, we put forward the method to compute the interdependent degree between information sources, and the evidence combination rule considering the interdependent degree between information sources to fuse the evidence information. Thirdly, the emergency alternative selection method based on the Pignistic probability, which can expand the difference of alternatives' reliability, is discussed. At last, an example analysis on multi-attribute emergency decision-making problem is applied to verify the effectiveness of the proposed method. The analysis results show that considering the interdependence between information sources will make the emergency decision-making more objective and scientific, as well as weaken the independence hypothesis on information sources and expand the application scope of evidence theory.
Combining cases mean clustering the series cases which the one or a group of criminals make. The information of combining cases are mainly from the victims, witnesses and police officers, so under the emergency situation, reflection and description of the case has a strong uncertainty, leading to information has the characteristics of multi-uncertainty. However there is the certain limitation for traditional method of multiple attribute clustering decision to research combining cases. In this paper, we study on the weight distribution of combining cases indicators deeply. At first, we take the combining cases as research object, point out the combining cases is typical multi-uncertainty case, and propose all uncertain parameters can be unified into the generalized standard interval grey numbers under a specific condition. Then we establish the generalized gray similarity model to calculate the similarity of attribute index as well as the whole case, and build the generalized interval grey entropy weight distribution model for combining cases indicators to solve the indicator weight of combining cases. Finally through the case study, we prove the rationality and feasibility of the model in this paper.
As an effective mechanism to draw users' intelligence, collaborative innovation in online community is beneficial for enterprises to find innovation directions. However, in the era of big data, information overload and distortion creates many challenges for knowledge acquisition from community, and most relevant researches focus on extracting the high-frequency knowledge with low utilization. Therefore, this article constructs a knowledge hypergraph model based on knowledge co-occurrence relationship to exploit users' experiences and innovation knowledge. And then we utilize the hMETIS algorithm and FP-Growth algorithm to analyze relationships among knowledge, to further achieve the valuable knowledge in different fields. We demonstrate the proposed method by a case study. This paper has certain significance in knowledge finding and data mining, and provides a guide for community management and products innovation.
Considering that different people are different in their linguistic preference and in order to determine the consensus state for supporting consensus decision making, this paper first proposes an interval composite scale based 2-tuple linguistic model, which realizes the process of translation from word to interval numerical and the process of retranslation from interval numerical to word. A consensus decision making model with personalized interval composite scales is proposed, which can provide different linguistic representation models for different decision-makers. This model includes a semantic translation and retranslation phase during decision process and determines the consensus state of the whole decision process. These models proposed take into full consideration that human language contains fuzziness and usually real-world preferences are uncertain, and provide efficient computation models to support consensus decision making.
This paper provides a spatial model in a linear monocentric city with considering welfare effect on heterogeneous commuters. Firstly, the population is assumed to comprise limited discrete group commuters and each group with the same value of time (VOT). Then, the analysis is extended to the individuals with continuous VOT from the discrete scenario. According to the landownership, we consider two polar cases with relevant conclusions. With absentee landownership, in the spatial equilibrium, every commuter is better off if the subsidy is enlarged and individual with high VOT benefits more than those with low values. However, subsidies for different modes have different effects. Automobile drivers will not be impacted from bus subsidies, whilst bus users suffer from automobile subsidies. The lower the bus users' VOT, the more they will lose. When all land is owned by city residents, some ones gains from subsides what others loses, on certain conditions.
The port integration problem in multi-port regions is studied from the perspective of maximizing the internal transport social welfare of the external transport system of a closed region in which the gateway ports are regarded as transport hubs. First, the economic principle for maximizing the social welfare is analyzed and a method to calculate the internal cost, which used to measure the internal transport social welfare of the external transport system, is proposed. Second, the optimal scale of port group in a multi-port region is determined through comparing the internal transport cost of different scale of port group. And then an integration method with multi-period investment and asset idling is proposed for excess port capacity in multi-port regions. Last, the Northeast China is selected for empirical study and its main port integration problem is investigated. Our research results should have important practical value and theoretical significance on port resources integration and cooperative operation in multi-port regions.
From ship operational point of view, a mixed operation of hub-and-spoke and multi-port calling is proposed for the reconstruction of a new liner's shipping network under asset integration. Based on the possible constraints to the integrated decision making of routes, flows and vessels in mixed operation, a mixed 0-1 linear programming mathematical model for minimizing the total costs is formulated and Lagrange decomposition algorithm combined with subgradient, preprocessing and feasible solution generation are put forward. Additionally, the method is verified to be capable of obtaining high computing performance to solve large-scale problem by numerical simulation for a set of instances. The results show that a new liner can obtain scale advantages from asset integration, depending on the re-optimization of the size and the structure of the fleet. A new liner should operate the main strings by opening an appropriate number of hub ports, and focus on promoting utilization with guaranteed priority of the proper matching of vessel types on the feeder rotations and full utilization of the mega-vessels on main strings.
Thyroid gland produces thyroid hormones to help the regulation of the body's metabolism. The under-activity and over-activity of thyroid hormone cause hypothyroidism and hyperthyroidism. The malfunction of thyroid hormone will lead to thyroid disease. In real medical conditions, thyroid disease data belong to typical imbalanced data. Traditional machine learning methods ignored the different structure (different imbalanced data varies in imbalanced ratio, dimension and the number of classes) among the imbalanced datasets. Consider the occurrence of imbalance and different structure among the thyroid disease data, this paper proposes an adaptive multiple classifier system (AMCS) for the imbalanced data distribution and variable types in different datasets. An adaptive multiple classifier system is constructed to select the optimal learning model to assist in the diagnosis of thyroid diseases adaptively. The adaptive multiple classifier system (AMCS) was formed by re-sampling, ensemble framework, feature selection, base classifiers and ensemble rules. The most popular algorithms are treated as candidates and the optimal algorithm in each component of MCS will be combined to deal with the classification task in an unique routine. Ten thyroid datasets with diverse structure are taken from KEEL and UCI for the experiment. The experimental results show that performance of the proposed approach is a competitive assistant in thyroid disease diagnosis.
As the product of web2.0 era, the emergence of social network sites make people bridge the traditional social gap caused by the temporal and spatial distance. Its wide spread and rapid development have changed our lifestyles dramatically. With the mass creation and frequent exchange of user generated content (UGC), an amount of interactive data and complex user relationship have been generated in the social network sites. This phenomenon attracts the attention of enormous researchers. However, extant researches of the tie strength mainly focused on the user attributes and social interactions. But they ignored the influence of network structure, and did not take into account the direction and habituation of social interactions. Hence, we propose a dissymmetrical tie strength estimation method based on user attributes, topology of networks and social interactions (DSTS-ATI). From the perspective of topology of networks, we consider not only the number of common neighbor nodes, but also the links between the nodes. The direction and habituation of social interactions affect the users' perception of tie strength. Therefore, this paper gives out the weights of different social interactions bidirectionally. The experimental results show that the proposed method enhances the accuracy of tie strength prediction. Further, it is beneficial to the research of opinion leaders discovery and the information dissemination mechanism.
In this paper, a deep learning regression model based on support vector machines and probabilistic output networks is proposed. Based on the deep structure of deep learning, generalization ability of support vector machines (SVM) and conditional probability estimation in probability output network, a multi-layer SVM is established. The problem of parameter selection in deep learning is avoided. Where the kernel widths were constructed as the form of a grid. The kernel parameters are obtained according to the maximum value of the p-values where chosen by the K-S test of the cumulative probability distribution and the empirical cumulative probability distribution of the corresponding β distribution. The corresponding output is the extracted feature, which is used as the input of the next layer model until the model reaches the end condition. The simulation experiments prove the effective of the proposed model by three standard regression data set.
Aiming at the problem that the uncertainty of generalized triangular fuzzy numbers (GTFN) exists in the mechanical structures for the reliability measurement, a discretization reliability calculation method based on evidence theory is proposed. Firstly, to properly construct the basic probability assignment (BPA) for uncertain variables, based on the discrete property of the BPA of the evidence variables, the deficiency of entropy equivalent method (EEM) is improved when the generalized triangular fuzzy number is defuzzified. On the basis of the improved entropy equivalent method (IEEM), a more simple defuzzification method, generalized density method (GDM), is proposed. Secondly, the evidence structure characterization of the random variables and GTFN are realized by the discretization method, the discrete continuous focal element sequences (or subintervals) are used as their evidence bodies, and then the BPA is constructed. Finally, the fusion rule of evidence theory is used to fuse the evidence bodies, in order to achieve the numerical calculation of the belief and plausibility. Combined with the Monte Carlo simulation (MCS) method, the feasibility of proposed approach is verified by taking the reliability calculation of crank-slider mechanism for example.
The layout of precipitation wireless sensor network node is very important for accurately analyzing the temporal and spatial distribution of precipitation and reducing the operating and maintenance costs. It is a key problem and difficulty in the construction of the internet of things observation system in smart basin. In this paper, according to the characteristics of the basin in the mountain region, a method for optimizing the design of precipitation wireless sensor network based on parallel computing architecture in the basin is proposed, which considered the restriction of road network. The method is used to analyze the rationality of the current station network and optimize the layout of the stations in the middle and lower reaches of the Yalong river basin. The results demonstrate that this sampling optimization method can give a rational layout of precipitation wireless sensor network which generally obtain the spatial distribution of precipitation. It can manyfold save the running time of the program and significantly improve the efficiency to optimize the design of precipitation wireless sensor network using the simulated annealing algorithm based on concurrent design.