A Decision Tree-Based Approach for Classifying and Characterizing the Failure Type of White Goods

After-sales service plays a vital role in the white goods industry, significantly affecting both customer satisfaction and operational performance. This paper presents a decision tree-based approach for classifying and characterizing failure types in white goods, using after-sales service data from a white goods manufacturer. We employ the Classification and Regression Tree (CART) algorithm to identify patterns in failure occurrences based on product category, region, usage duration, and brand. The model generates interpretable decision rules, providing insights into the factors contributing to failures. The results reveal that product category and region are the most significant factors influencing product failures. These findings support manufacturers and service providers in optimizing maintenance strategies and improving service operations. The proposed approach enhances decision-making processes in after-sales service, leading to higher customer satisfaction and extended product life cycles.