Abstract
Objectifying claims filed during the warranty period, analyzing the current circumstances and improving on the problem in question is an activity worth doing that could reduce the likelihood of claims to occur, cut down on the costs, and enhance the corporate image of the manufacturer. Existing analyses of claims are confronted with two problems. First, you can't precisely assess the risks of claims involved by means of the value of claims per 100 products alone. Second, even in a normal state, the existing approach fails to capture the probabilistic conflicts that escape the upper control limit of claims, thus leading to wrong control activities. To solve the first problem, this paper proposed that a time series detection concept where the claim rate is monitored based on the date when problems are processed and a hazard function for expression of the claim rate be utilized. For the second problem, this paper designed a model whereby to define a normal state by making use of PID (Proportion, Integral, Differential) and infer by way of a fuzzy concept. This paper confirmed the validity and applicability of the proposed approach by applying methods suggested in the actual past data of warranty claims of a large-scaled automotive firm, unlike hypothetical simulation data, in order to apply them directly in industrial job sites, as well as making theoretical suggestions for analysis of claims.