Data-Driven Estimation of Heavy-Truck Residual Value at the Buy-Back

Abstract

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.

Empowering Commercial Vehicles through Data-Driven Methodologies

“…Instead, the RUL estimation consists of estimating the residual life of a given vehicle (in terms of the number of kilometers it can still cover or days of activity). This information can be beneficial when referring to commercial vehicles, for example, during a buy-back operation, as illustrated in [10]. Work with a similar aim has been proposed in [11], where the authors propose a cloud-based infrastructure capable of providing an online assessment of the residual helpful life and end of life (EOL) of the vehicle under analysis.…”

“…Not much work in this context has been performed on heavy trucks at present, leaving plenty of room for new analyses and experiments. The work presented in [10] is based on a situation similar to the current one; however, the analyses performed are completely different in terms of both the research objective and methodology adopted. Only a portion of the analyzed data is common to the current study.…”

“…Different from a research activity, such as [10], in which the only parameters considered are those monitored by the various sensors, here we enrich the available telematics data with a proper feature modeling step. The definition of specific key performance indicators (KPIs) allows capturing the knowledge hidden in the various parameters being monitored.…”