Measuring the Effectiveness of AI-Powered Training in Luxury Automotive Retail Sales Networks
DOI:
https://doi.org/10.5281/zenodo.20728968Keywords:
Automotive industry, Sales forecasting, Digital transformation, Machine learning, Production planning, vehicle sales dataAbstract
The vehicle valuation process in the dynamic secondary automotive market is a challenging task because the vehicle value depends on condition, mileage, and the constantly changing market in a non-linear relationship. The objective of this study is to create a very accurate, scalable predictive model of vehicle selling prices that combines institutional market benchmarks with vehicle physical characteristics. For this purpose, a comprehensive end-to-end pipeline is designed based on automatic column transformations that convert high-dimensional categorical features into continuous numerical features. In this study, three advanced ensemble learning models XGBoost (XGB) Random Forest (RF) and Gradient Boosting (GB), were considered and compared to the traditional models. The results show that ensemble architectures outperform individual architectures at predicting accuracy. The Gradient Boosting model had the best empirical performance with a score of 0.976, MSE of 2161666.55 and a RMSE of 1,470.26, followed closely by Random Forest and XGBoost with an score of 0.975. The proposed models were rigorously validated against existing models such as Support Vector Regression, LSTM, KNN, Linear Regression, and Prophet, where the results presented that the proposed models significantly outperform the traditional models. Results from the feature importance mapping confirmed that the Manheim Market Report (MMR) remains most useful as a predictive indicator, and the results from the residual diagnostics showed performance boundaries in the premium asset segments. The overall contribution of this research is a validated data-driven methodology that improves the accuracy of valuing assets in real-time, and offers a solid framework for structured data prediction in the secondary markets.
References
[1] A. Gopalakrishna, “Machine Learning in Online Car Retail: Enhancing User Experience and Conversion Rates,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 12, no. 9, pp. 1296–1310, Sep. 2024, doi: 10.22214/ijraset.2024.64310.
[2] C. Patel, “Generative AI for Personalized Marketing and Customer Experience in E-Commerce,” Int. J. Emerg. Res. Eng. Technol., vol. 7, no. 1, pp. 12–19, 2026, doi: 10.63282/3050-922X.IJERET-V7I1P103.
[3] V. Sanikal, “Thermal Intelligence Big Data and AI for Sustainable Battery and Cabin Heat Management in Electric vehicle,” Am. J. Eng. Technol., vol. 07, no. 11, pp. 129–142, Nov. 2025, doi: 10.37547/tajet/v7i11-301.
[4] P. Parida and N. Senguttuvan, “Responsible Utilization of Cloud in Retail Banking Ecosystem,” Int. J. Comput. Appl., vol. 187, no. 49, pp. 34–39, Oct, 2025, doi: 10.5120/ijca2025925835.
[5] P. Kumar, V. Begum, A. Vij, and E. Y. Masoud, “Sales Pressure and Ethical Selling: Moral Reasoning Framework for Business and Marketing Decisions,” FIIB Bus. Rev., Apr. 2025, doi: 10.1177/23197145251330150.
[6] K. Trianti, M. R. Zaini, and Y. N. Zakkiya, “Marketing Strategies at Retail Be Smart in Increasing Sales,” Int. J. Entrep. Bus. Adm., vol. 2, no. 2, pp. 58–75, Aug. 2024, doi: 10.33474/ijeba.v2i2.22428.
[7] K. Dixit, “Predictive Analytics in Business Intelligence for Sales Forecasting,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 03, no. 01, p. 981, Sep. 2023, doi: 10.48175/IJARSCT-12750G.
[8] C. Patel, “Integration of AI in Customer Relationship Management (CRM) for Improved Sales Outcomes,” Int. J. Emerg. Res. Eng. Technol., vol. 6, no. 4, pp. 137–145, 2025, doi: 10.63282/3050-922X.IJERET-V6I4P117.
[9] W. Huang, L. Wu, X. Zeng, and Y. Sun, “Analysis of spatial distribution characteristics of electric vehicle sales and service shops and the corresponding influencing factors,” Trans. GIS, vol. 27, no. 5, pp. 1357–1390, Aug. 2023, doi: 10.1111/tgis.13070.
[10] S. Derhami and B. Montreuil, “Estimation of potential lost sales in retail networks of high-value substitutable products,” IISE Trans., 2022, doi: 10.1080/24725854.2021.1969484.
[11] C. Patel, “Effect of Digital Transformation on Customer Engagement in Retail Industries : A Comparative Review,” J. Technol., vol. 10, no. 1, pp. 165–174, 2022.
[12] V. Sohrabpour, P. Oghazi, R. Toorajipour, and A. Nazarpour, “Export sales forecasting using artificial intelligence,” Technol. Forecast. Soc. Change, vol. 163, p. 120480, Feb. 2021, doi: 10.1016/j.techfore.2020.120480.
[13] S. Pareek, R. Kumar, S. Dasi, K. Kaur, and A. Singh, “Digital Transformation and Its Impact on Business Performance in the Retail Industry,” in Proceedings of the 2025 International Conference on Technology Enabled Economic Changes, InTech 2025, 2025. doi: 10.1109/InTech64186.2025.11198212.
[14] Y. Cui, Y. Zhou, T. Zhou, J. Wen, and W. Liang, “Marketing Strategies in the Digital Retail Era: A Case Study on Xiaomi’s Omnichannel Approach and Its Impact on Brand Recognition, Sales, and User Experience,” Adv. Eng. Technol. Res., vol. 13, no. 1, p. 477, Mar. 2025, doi: 10.56028/aetr.13.1.477.2025.
[15] H. Ravilla, “Building Scalable Applications with Heroku and Salesforce Integration,” Am. J. Technol., vol. 4, no. 3, Dec, pp. 15–36, 2025.
[16] Y. Patel, “Dynamic Pricing Optimization Using Real-Time Demand Elasticity Modeling in Online Retail,” Am. J. Auton. Syst. Robot. Eng., vol. 1, pp. 721–744, Januray, 2021.
[17] M. Mazur, O. Stopka, M. Stopková, J. Hanzl, A. Borucka, and R. Czerniak, “Assessing the Success of Automotive Sales Transactions Using Selected Machine Learning Algorithms,” Appl. Sci., vol. 15, no. 21, p. 11562, Oct. 2025, doi: 10.3390/app152111562.
[18] F. Du, Y. Feng, and L. He, “A Hybrid Deep Learning Model for Car Sales Forecasting,” in Proceedings of the 2025 6th International Conference on Big Data Economy and Information Management, New York, NY, USA: ACM, Dec. 2025, pp. 1411–1419. doi: 10.1145/3800000.3800217.
[19] S. Bergmann and S. Feuerriegel, “Machine learning for predicting used car resale prices using granular vehicle equipment information,” Expert Syst. Appl., vol. 263, p. 125640, Mar. 2025, doi: 10.1016/j.eswa.2024.125640.
[20] V. Golderzahi and H.-K. K. Pao, “Revenue forecasting in smart retail based on customer clustering analysis,” Internet of Things, vol. 27, p. 101286, Oct. 2024, doi: 10.1016/j.iot.2024.101286.
[21] M. Sajawal, S. Usman, H. Alshaikh, A. Hayat, and M. U. Ashraf, “Predictive Analysis of Retail Sales Forecasting using Machine Learning Techniques,” vol. 6, pp. 23–33, 2023, doi: 10.54692/lgurjcsit.2022.06004399.
[22] S. Tarakampet and S. B. S. Ali, “Integrating Custom Enterprise Applications with Legacy Systems for Risk Management: A Modern Enterprise Approach,” Int. J. Trend Sci. Res. Dev., vol. 10, no. 1, pp. 765–770, 2026.
[23] M. Zubair, A. Waleed, A. Rehman, F. Ahmad, M. Islam, and S. Javed, “Machine Learning Insights into Retail Sales Prediction: A Comparative Analysis of Algorithms,” in 2024 Horizons of Information Technology and Engineering (HITE), 2024, pp. 1–7. doi: 10.1109/HITE63532.2024.10777132.
[24] Y. Sun and T. Li, “A transformer-based framework for enterprise sales forecasting,” PeerJ Comput. Sci., vol. 10, p. e2503, Nov. 2024, doi: 10.7717/peerj-cs.2503.
[25] K. Y. Wen, M. H. Joseph, and V. Sivakumar, “Big Mart Sales Prediction using Machine Learning,” EAI Endorsed Trans. Internet Things, vol. 10, pp. 1–6, Jun. 2024, doi: 10.4108/eetiot.6453.
[26] C. Anusha and S. Maiti, “Optimizing Retail Inventory and Sales Through Advanced Time Series Forecasting Using Fine Tuned PrGB Regressor,” IEEE Access, vol. 13, pp. 165328–165341, 2025, doi: 10.1109/ACCESS.2025.3605229.
[27] J. Prajapati, K. Patel, K. Shukla, J. Suthar, and D. Y. Farooqui, “Car Price Prediction Using Machine Learning Techniques,” J. Emerg. Technol. Innov. Res., vol. 12, no. 3, pp. i637–i643, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mohit Kohli (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
