Can machine learning techniques predict customer dissatisfaction? A feasibility study for the automotive industry

Abstract

The automotive industry is in the strongest competition ever, as this sector gets disrupted by new arising competitors. Providing services to maximum customer satisfaction will be one of the most crucial competitive advantages in the future. Around 1 Terabyte of objective data is created every hour today. This volume will significantly grow in the future by the increasing number of connected services within the automotive industry. However, customer satisfaction determination is solely based on subjective questionnaires today without taking the vast amount of objective sensor and service process data into account. This work presents an industrial application that fills this lack of research and thus provides a solution with a high practical impact to survive in the tough competition of the automotive industry. Therefore, the work addresses these fundamental business questions: 1) Can dissatisfied customers be classified based on data that is produced during every service visit? 2) Can the dissatisfaction indicators be derived from service process data? A machine learning problem is set up that compared 5 classifiers and analyzed data from 19,008 real service visits from an automotive company. The 105 extracted features were drawn from the most significant available sources: warranty, diagnostic, dealer system and general vehicle data. The best result for customer dissatisfaction classification was 88.8% achieved with the SVM classifier (RBF kernel). Furthermore, the 46 most potential indicators for dissatisfaction were identified by the evolutionary feature selection. Our system was capable of classifying customer dissatisfaction solely based on the objective data that is generated by almost every service visit. As the amount of these data is continuously growing, we expect that the presented data-driven approach can achieve even better results in the future with a higher amount of data.