A Comprehensive Approach to Residual Value Analysis in the Luxury Automotive Market

Global automotive markets have introduced new complexities, from the surge in powertrain diversity to evolving consumer purchasing habits. In the luxury car segment, residual value (RV), the car's actual value at the end of ownership, is particularly significant. A high RV translates into lower overall ownership costs, as the car retains more of its value over time, which can boost demand as well as leasing margin. For this reason, the analysis of RV offers key insights for strategic decision-making. The present study leverages a large-scale global dataset spanning a 10-year period, capturing both internal vehicle features and three available external market conditions (CPI, unemployment rate, and 10-year bond yield). Our approach employs machine learning techniques, particularly CatBoost, achieving a mean absolute percentage error of around 5%, deemed highly acceptable within the industry. Moreover, a novel method to enhance the reliability and interpretability of RV estimations is proposed by quantifying depreciation thresholds and mitigating distortions related to sample composition via a "Standard Vehicle" concept. The approach has been validated by Ferrari S.p.A., the provider of the data, serving as a robust tool for automotive industry stakeholders.