Clustering method for data with mixed parametric structures

Abstract

Regarding the structural complexity of data, stratification of the data using a clustering method is important for constructing a model based on more detailed characteristics of the data. In particular, the data such as product failures shows there are various processes causing failures. This implies it is necessary to stratify the data for more precise analysis. However, these stratification factors are rarely acquired as data, and it is often difficult to grasp them. In this research, we propose a clustering method for extracting data structures that follow a Weibull distribution event occurrence data in a certain market product.