Prediction of warranty cost and warranty period using neuro-fuzzy approach: case study of automobile warranty data

Nowadays, warranty has its own priority in business strategy for a manufacturer to protect their benefit as well as the intense competition between the manufacturers. In fact, warranty is a contract between manufacturer and buyer in which the manufacturer gives the buyer certain assurances as the condition of the property being sold. In industry, an accurate prediction of optimal warranty period and warranty costs is often counted by the manufacturer. A warranty period may be unprofitable for the manufacturers if the choice of duration given is either too short or too long. Same thing goes to warranty cost which is an underestimation or overestimation of the warranty cost may have a high influence to the manufacturers. This paper presents a methodology to adapt historical maintenance warranty data with neuro-fuzzy approach. The main motivations for conducting this paper are simplicity and less computational mass of the neuro-fuzzy based on previous studies on this method compared to single method such neural network and fuzzy logic