Journal of The Japanese Society for Quality Control

In order to satisfy consumers' needs more appropriately, it is very important to classify consumers into several segments which have similar preferences and to present products based on characteristics of each segment. In this paper, we first propose new methods which directly estimate the utility function of segment from the difference of subjects' evaluation of profiles in the same segment without finding the part-worth values of each subject. Secondly, we apply these methods to actual products and show their efficiencies and the phenomena in Marketing, such as the cannibalism, by the utility function of segment incorporating the overlapping clustering. As a result, we clarified that these proposed methods could give more detailed analyses at the product-planning stage.

View full abstract

We often manage progress by the number of completed programs in the coding and unit test process of large-scale software development. Usually, the graph of progress draws an S-curve that tends to be late. Terefore, it is difficult to judge only by the graph of progress whether the project proceeds favorably or not. To solve this problem. we investigate the progress data of real large-scale project that contains five teams and the condition of actual site. Eventually, we disocvered different characters in working and significant changes of productivity according to "begin", "middle" and "end" of the coding and unit test process. From this investigation, we propose "the four divided process control method" that divide the coding and unit test process in four divisions. Using this way of thinking, we can manage a long and monotonous prodess more securely by new control items of each division. And, we discuss the estimation of personnel number in coding and unit test process using "the four-divisons management"

View full abstract

In manufacturing, a change sometimes occurs in the raw materials and/or in the production process after which the lifetime distribution of the products is different from the distribution before the change. Usually the time at which the change occurred is unknown. In this article, we investigate a method to detect the change-point when only the marginal failure counts for the product are available. We present a nonhomogeneous Poisson process model for the repairable products and discuss nonparametric estimation of the parameters, the mean number of failures per product, before and after the change. We apply the EM algorithm to obtain maximum likelihood estimates of the parameters and use the Akaike Information Criterion (AIC) to detect the change-point. An example is given which is based on the field reliability data of an electrical product, and simulation studies are conducted to evaluate the performance of the proposed method.

View full abstract

Show abstractHide abstract

The purpose of this article is to construct the model of the software development process which usually consists of some steps, "analysis of requirement", "definition of functions" and so on, and to discuss the policies for managing the process efficiently, and to prepare the practical and easy implement. First we define the two categories of product specifications according to the mechanism which organizes the appropriate specifications of the product in the mind of the designer. These are called "Tacit Specification" and "Peculiar Specification". The former is the specification which is made unconsciously of the memories/knowledge of the designer. And latter is the one which is peculiar to the product and can not be made only of the memories/knowledge of the designer. Secondly, based on these categories we construct the model of the product development process, which consists of the 2 different kinds of processes which organize the tacit and peculiar specification respectively. And managerial policies for these processes are discussed especially focusing on the prevention and the quick detection of the unpredictable design changes. For this purpose, the easy tool which is the application of IDEF3 is prepared. Finally, these issues are verified using the field studies of the operational software development projects at production plant.

View full abstract

Download PDF (1475K)

Register with J-STAGE for free!