In a context of deep transformation of the entire automotive industry, starting from pervasive and native connectivity, commercial vehicles (heavy, light, and buses) are generating and transmitting much more data than passenger cars, with a much higher expected value, motivated by the higher costs of the vehicles and their added-value related businesses, such as logistics, freight, and transportation management. This paper presents a data-driven and unsupervised methodology to provide a descriptive model assessing the residual value estimates of heavy trucks subject to buy-back. A huge amount of telematics data characterizing the actual usage of commercial vehicles is jointly analyzed with different external conditions (e.g., altimetry), affecting the truck's performance to estimate the devaluation of the vehicle at the buyback. The proposed approach has been evaluated on a large set of real-world heavy trucks to demonstrate its effectiveness in correctly assessing the real status of wear and residual value at the end of leasing contracts, to provide a few and quantitative insights through an informative, interactive and user-friendly dashboard to make a proper decision on the next business strategies to be adopted. The proposed solution has already been deployed by a private company within its data analytics services since (1) an interpretable descriptive model of the main factors/parameters and corresponding weights affecting the residual value is provided and (2) the experimental results confirmed the promising outcomes of the proposed data-driven methodology. INDEX TERMS Business vs data-driven methodologies, Automotive industry, Commercial Vehicles, Residual value estimation.

In the era of “connected vehicles,” i.e., vehicles that generate long data streams during their usage through the telematics on-board device, data-driven methodologies assume a crucial role in creating valuable insights to support the decision-making process effectively. Predictive analytics allows anticipation of vehicle issues and optimized maintenance, reducing the resulting costs. In this paper, we focus on analyzing data collected from heavy trucks during their use, a relevant task for companies due to the high commercial value of the monitored vehicle. The proposed methodology, named TETRAPAC, offers a generalizable approach to estimate vehicle health conditions based on monitored features enriched by innovative key performance indicators. We discussed performance of TETRAPAC in two real-life settings related to trucks. The obtained results in both tasks are promising and able to support the company’s decision-making process in the planning of maintenance interventions.