Predicting Customer Satisfaction of Luxury Watches Using ID3 Algorithm

It is generally believed that luxury watches are bought by the rich and elite as a status symbol. But customer satisfaction is crucial for repeat buying, the customer base being comparatively small. The aim of the study was to find out the factors on the basis of which customer satisfaction can be predicted and the hierarchy in which these factors impact customer satisfaction. Information was collected from the customers of the luxury watch division of Pantaloons, Junction Mall in Durgapur, West Bengal. First exploratory factor analysis was used to identify the factors impacting the satisfaction level. The factors identified were Performance, Design, Quality, Marketing Efforts, and Concern For Status. The ID3 decision tree algorithm was used to classify the customers into three levels high satisfaction, moderate satisfaction, and low satisfaction with their purchase. Confusion matrix and ROC curve were used for downscaling the robustness of the model. The overall accuracy of the model was 89.47%.