A stochastic model is developed for describing a market lifecycle expressed in terms of the number of corporations N in the market. Each corporation independently determines the probability of market entry if it is not in the market yet or the probability of market retreat if it is already in the market. These probabilities may depend on time t, the number of corporations in the market at time t and the number of corporations which have retreated from the market by time t. Of interest is the number of corporations in the market at time t, thereby enabling one to analyze the market lifecycle in terms of strategic actions of individual corporations. Rigorous analysis of this process becomes numerically intractable since the corresponding state space explodes as N increases. In order to overcome this difficulty, we propose temporally inhomogeneous marginal processes describing the states of individual corporations. The process of interest is then approximated as the independent sum of such marginal processes. An algorithmic procedure is developed for computing the probability distribution of the number of corporations in the market based on spectral analysis of the temporally inhomogeneous marginal processes combined with a bivariate generating function approach. Corporations are classified into three groups: RT (Risk-Taking), RN (Risk-Neutral), and RA (Risk-Aversive), where these groups are characterized by specifying the transition probabilities of the underlying marginal processes. It is numerically observed that any class alone is not sufficient to form a market and a typical market lifecycle emerges only through the presence of an appropriate combination of corporations from the three classes.

抄録全体を表示

This paper considers one-machine sequencing situations with linear costs in which the urgency of players is private information. To study strategic behavior of players based on neighbor switches we associate with such a situation a Bayesian game where the utility functions are based on gain split rules and study whether the truth-telling strategy profile is an equilibrium of the game. The existence of such truth-telling equilibria turns out to be exceptional.

抄録全体を表示

In this study, we propose a new solution approach for the Transportation Fleet Maintenance Scheduling Problem (TFMSP). Before presenting our solution approach, we first review Goyal and Gunasekaran's [International Journal of Systems Science, 23 (1992) 655-659] mathematical model and their search procedure for determining the economic maintenance frequency of a transport fleet. To solve the TFMSP, we conduct a full analysis on the mathematical model. By utilizing our theoretical results, we propose an efficient search algorithm that finds the optimal solution for the TFMSP within a very short run time. Based on our experiments using random data, we conclude that the proposed search algorithm out-performs Goyal and Gunasekaran's search procedure.

抄録全体を表示

This paper proposes an operational approach (based on marginal actions) to specify multiattribute utility functions, which allows us to easily rank alternatives from criteria relevant to the manager, the customer or any other decision maker without heuristic remedies, imprecision or loss of generality. Marginal actions are fictitious alternatives which play a key role in preference analyses as a tool recently introduced for the ranking treatment of decision tables. As usual in multi-attribute value theory, preferential independence is assumed. A practical large-scale case in the textile industry to rank commercial fabrics -characterized by seven quality factors- is developed.

抄録全体を表示

This paper deals with the use of neural network rule extraction techniques based on the Genetic Programming (GP) to build intelligent and explanatory evaluation systems. Recent development in algorithms that extract rules from trained neural networks enable us to generate classification rules in spite of their intrinsically black-box nature. However, in the original decompositional method looking at the internal structure of the networks, the comprehensive methods combining the output to the inputs using parameters are complicated. Then, in our paper, we utilized the GP to automatize the rule extraction process in the trained neural networks where the statements changed into a binary classification. Even though the production (classification) rule generation based on the GP alone are applicable straightforward to the underlying problems for decision making, but in the original GP method production rules include many statements described by arithmetic expressions as well as basic logical expressions, and it makes the rule generation process very complicated. Therefore, we utilize the neural network and binary classification to obtain simple and relevant classification rules in real applications by avoiding straightforward applications of the GP procedure to the arithmetic expressions. At first, the pruning process of weight among neurons is applied to obtain simple but substantial binary expressions which are used as statements is classification rules. Then, the GP is applied to generate ultimate rules. As applications, we generate rules to prediction of bankruptcy and creditworthiness for binary classifications, and the apply the method to multi-level classification of corporate bonds (rating) by using the financial indicators.

抄録全体を表示