Revenue Score Modeling for Optimal Retention and Disposal Timing in Rental Vehicle Fleets

Vitalii Kolesnykov

Vitalii Kolesnykov K Motors In, Founder, USA

Keywords: rental fleet management, dynamic pricing, vehicle lifecycle scoring, residual value forecasting, demand elasticity, dynamic programming, depreciation cost optimization, fleet disposition timing

Abstract

Condition-based vehicle replacement scoring reduces fleet costs when computed independently of pricing, generating annual savings exceeding thirteen million dollars in a documented telecommunications fleet, yet this decoupling leaves the marginal wear cost of individual bookings absent from the pricing decision. This paper tests a coupled architecture in which a bounded composite lifecycle score, built from six mechanical and operational sub-indices, enters simultaneously into a price-ceiling constraint, a multiplicative residual-value correction, and a two-stage dynamic-programming and closed-form pricing solver. Monte Carlo simulation across synthetic fleets of 200 to 2000 vehicles, run for 2400 replications against two named baselines, a static replacement-score architecture and a fixed condition-gated architecture, isolates the contribution of price coupling from that of scoring alone. The coupled architecture reduces depreciation cost per revenue dollar by 16.8 to 17.0 percent against the score-only baseline and by 10.9 to 11.3 percent against the static-gated baseline, with 61 percent of the total reduction attributable to the pricing-ceiling mechanism rather than to scoring and eligibility gating. Residual value realization rises from 0.87 to 0.94 at disposition under identical projection functions, a difference traced to disposition timin. The alternating solver reaches a 2.4 percent optimality gap against an exact mixed-integer benchmark at fleet size 50, converging in three to six iterations. The coupling advantage collapses to a statistically indistinguishable margin when demand elasticity falls below unity, since the pricing ceiling binds structurally in that regime and cannot serve as a coupling instrument, confining the confirmed effect to elastic-demand conditions.

References

Ayuso, M., Guillén, M., & Nielsen, J. P. (2019). Improving automobile insurance ratemaking using telematics: Incorporating mileage and driver behaviour data. Transportation, 46(3), 735–752. https://doi.org/10.1007/s11116-018-9890-7
de Albuquerque Felizola Romeral, P. A., & Zancul, E. (2025). Total cost of ownership of electric vehicles: A synthesis of critical factors. The Journal of Engineering, 2025, Article e70113. https://doi.org/10.1049/tje2.70113
Dietz, D. C., & Katz, P. A. (2001). U S WEST implements a cogent analytical model for optimal vehicle replacement. Interfaces, 31(5), 65–73.
Fan, W., Machemehl, R. B., & Gemar, M. D. (2012). Optimization of equipment replacement. Transportation Research Record, 2292(1), 178–184. https://doi.org/10.3141/2292-19
Feng, W., & Figliozzi, M. (2014). Vehicle technologies and bus fleet replacement optimization: Problem properties and sensitivity analysis utilizing real-world data. Public Transport, 6(1–2), 137–157. https://doi.org/10.1007/s12469-014-0086-z
Hartman, J. C., & Murphy, A. (2006). Finite-horizon equipment replacement analysis. IIE Transactions, 38(5), 409–419.
Kim, M., Choi, J., Kim, J., Kim, W., Baek, Y., Bang, G., Son, K., Ryou, Y., & Kim, K.-E. (2023). Trustworthy residual vehicle value prediction for auto finance. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 15537–15544. https://doi.org/10.1609/aaai.v37i13.26842
Lessmann, S., Listiani, M., & Voß, S. (2010). Decision support in car leasing: A forecasting model for residual value estimation. In Proceedings of the 31st International Conference on Information Systems (ICIS 2010). Association for Information Systems.
Lessmann, S., & Voß, S. (2017). Car resale price forecasting: The impact of regression method, private information, and heterogeneity on forecast accuracy. International Journal of Forecasting, 33(4), 864–877. https://doi.org/10.1016/j.ijforecast.2017.04.003
Li, D., & Pang, Z. (2017). Dynamic booking control for car rental revenue management: A decomposition approach. European Journal of Operational Research, 256(3), 850–867. https://doi.org/10.1016/j.ejor.2016.06.048
Moosavi, S., & Ramnath, R. (2023). Context-aware driver risk prediction with telematics data. Accident Analysis & Prevention, 192, Article 107269. https://doi.org/10.1016/j.aap.2023.107269
Oliveira, B. B., Carravilla, M. A., & Oliveira, J. F. (2017). Fleet and revenue management in car rental companies: A literature review and an integrated conceptual framework. Omega, 71, 11–26. https://doi.org/10.1016/j.omega.2016.09.011
Oliveira, B. B., Carravilla, M. A., & Oliveira, J. F. (2018). Integrating pricing and capacity decisions in car rental: A matheuristic approach. Operations Research Perspectives, 5, 334–356. https://doi.org/10.1016/j.orp.2018.10.002
Rashed, A., Jawed, S., Rehberg, J., Grabocka, J., Schmidt-Thieme, L., & Hintsches, A. (2020). A deep multi-task approach for residual value forecasting. In U. Brefeld, E. Fromont, A. Hotho, A. Knobbe, M. Maathuis, & C. Robardet (Eds.), Machine learning and knowledge discovery in databases: ECML PKDD 2019 (Lecture Notes in Computer Science, Vol. 11908, pp. 470–485). Springer. https://doi.org/10.1007/978-3-030-46133-1_28
Redmer, A. (2022). Strategic vehicle fleet management: A joint solution of make-or-buy, composition and replacement problems. Journal of Quality in Maintenance Engineering, 28(2), 327–349. https://doi.org/10.1108/JQME-04-2020-0026
Waddell, R. (1983). A model for equipment replacement decisions and policies. Interfaces, 13(4), 1–7. https://doi.org/10.1287/inte.13.4.1
Xu, M., Meng, Q., & Liu, Z. (2018). Electric vehicle fleet size and trip pricing for one-way carsharing services considering vehicle relocation and personnel assignment. Transportation Research Part B: Methodological, 111, 60–82. https://doi.org/10.1016/j.trb.2018.03.001