O
Orclever
Back to Journal
Research Article Open AccessOrclever Native

A Temporal-Weighted Hybrid Recommender for B2B Vehicle Auctions Using Word2Vec Embeddings

Selçuk Bayracı1✉,
Uğur Barış Öztürk2,
Turgay Tugay Bilgin3
1Borusan Otomotiv R&D Center
2Borusan Otomotiv R&D Center
3Bursa Technical University
Published:December 19, 2025
DOI: 10.56038/ejrnd.v5i1.718
Vol. 5, No. 1

Abstract

Used car auction platforms face unique challenges in personalized recommendation due to extreme data sparsity, high inventory turnover, and real-time operational constraints. This study develops and evaluates a hybrid recommendation system combining Word2Vec embeddings for categorical vehicle attributes with standardized numerical features, applying temporal decay weighting to prioritize recent user interactions. Deployed on Azure infrastructure, the system was evaluated using 12 months of transaction data from a Turkish B2B auction platform comprising 5,322 users, 24,987 vehicles, and 1.87 million interactions. Offline evaluation demonstrates superior performance over baselines (Hit Rate@10: 0.456 vs 0.234 popularity baseline, 94.9% improvement). Production deployment over six months (April–September 2025) generated 977 recommendation-driven sales representing 15.26% of total platform transactions and 17.27M TL in commission revenue. Quasi-experimental analysis revealed a 26.7% increase in monthly purchase frequency among active users, yielding 420 incremental transactions. Results demonstrate how interpretable temporal-weighted embedding models generate measurable commercial value in high-turnover, data-sparse B2B marketplaces.

Keywords
Recommendation systemsVehicle auctionsWord2vec embeddingsTemporal weightingB2B analytics

References

  1. 1.S. Talati, et al., “Recommendation System for Automobile Purchasing: A Survey,” International Journal of Computer Applications, NCACIT-2016, pp. 23-27, 2016.
  2. 2.B. Sabiri, A. Khtira, B. El Asri, and M. Rhanoui, “Hybrid Quality-Based Recommender Systems: A Systematic Literature Review,” Journal of Imaging, vol. 11, no. 1, p. 12, 2025. https://doi.org/10.3390/jimaging11010012DOI
  3. 3.S. Yamarthi, B. Chintala, and P. H. Basha, “A Deep Learning Based Hybrid Recommendation Model for Internet Users,” Scientific Reports, vol. 14, p. 79011, 2024. https://doi.org/10.1038/s41598-024-79011-zDOI
  4. 4.S. Lv, J. Wang, F. Deng, et al., “A Hybrid Recommendation Algorithm Based on User Nearest Neighbor Model,” Scientific Reports, vol. 14, p. 17119, 2024. https://doi.org/10.1038/s41598-024-66393-3DOI
  5. 5.“Hybrid Attribute-Based Recommender System for Personalized E-Learning with Emphasis on Cold Start Problem,” Frontiers in Computer Science, vol. 6, 2024. https://doi.org/10.3389/fcomp.2024.1404391DOI
  6. 6.Y. Koren, “Collaborative Filtering with Temporal Dynamics,” in Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, 2009, pp. 447-456. https://doi.org/10.1145/1557019.1557072DOI
  7. 7.Y. Kim, Y. Lee, V. Yuan, A. Lee, and Y. Lee, “A Temporal Graph Network Framework for Dynamic Recommendation,” arXiv preprint arXiv:2403.16066, 2024.
  8. 8.“TCGC: Temporal Collaboration-Aware Graph Co-Evolution Learning for Dynamic Recommendation,” ACM Transactions on Information Systems, vol. 43, no. 1, Article 5, 2025. https://doi.org/10.1145/3687470DOI
  9. 9.S. Ben Abdrabbah, S. Mallek, and N. Ben Amor, “Dynamic Communities: A Novel Recommendation Approach for Individuals and Groups,” in Lecture Notes in Computer Science, vol. 14546, Springer, 2024, pp. 187-201. https://doi.org/10.1007/978-3-031-55326-4_9DOI
  10. 10.P. Li and A. Tuzhilin, “A Dynamical System Framework for Exploring Consumer Trajectories in Recommender System,” SSRN Working Paper, 2024. https://doi.org/10.2139/ssrn.4847168DOI
  11. 11.M. G. Ozsoy, “From Word Embeddings to Item Recommendation,” arXiv preprint arXiv:1601.01356, 2016.
  12. 12.H. Caselles-Dupré, F. Lesaint, and J. Royo-Letelier, “Word2vec Applied to Recommendation: Hyperparameters Matter,” in Proceedings of the 12th ACM Conference on Recommender Systems, ACM, 2018, pp. 352-356. https://doi.org/10.1145/3240323.3240377DOI
  13. 13.E. Ordentlich, L. Yang, A. Feng, P. Cnudde, and G. Owens, “Tuning Word2vec for Large Scale Recommendation Systems,” in Proceedings of the 14th ACM Conference on Recommender Systems, ACM, 2020. https://doi.org/10.1145/3383313.3418486DOI
  14. 14.J. Szymański, M. Operlejn, and P. Weichbroth, “Enhancing Word Embeddings for Improved Semantic Alignment,” Applied Sciences, vol. 14, no. 24, p. 11519, 2024. https://doi.org/10.3390/app142411519DOI
  15. 15.S. Talati, et al., “Recommendation System for Automobile Purchasing: A Survey,” International Journal of Computer Applications, NCACIT-2016, pp. 23-27, 2016.
  16. 16.L. B. Thomas and V. Vaidhehi, “The Design of Web Based Car Recommendation System using Hybrid Recommender Algorithm,” International Journal of Engineering & Technology, vol. 7, no. 3.4, pp. 192-196, 2018.
  17. 17.G. Prabowol, M. Nasrun, and R. A. Nugrahaeni, “Recommendations for Car Selection System Using Item-Based Collaborative Filtering (CF),” in IEEE International Conference on Signals and Systems (ICSigSys), IEEE, 2019, pp. 116-119. https://doi.org/10.1109/ICSigSys.2019.8810967DOI
  18. 18.H.-W. Liu, J.-Z. Wu, and F.-L. Wu, “An App-Based Recommender System Based on Contrasting Automobiles,” Processes, vol. 11, no. 3, p. 881, 2023. https://doi.org/10.3390/pr11030881DOI
  19. 19.R. Xu, “A Hybrid Recommendation System for Online Car Auction Platform and Product Review,” Master’s Paper, University of North Carolina at Chapel Hill, 2021.
  20. 20.N. L. Le, M.-H. Abel, and P. Gouspillou, “Towards an Ontology-based Recommender System for the Vehicle Domain,” in 3rd International Conference on Deep Learning, Artificial Intelligence and Robotics (ICDLAIR), 2021, pp. 107-116.
  21. 21.P. Boteju and L. Munasinghe, “Vehicle Recommendation System using Hybrid Recommender Algorithm and Natural Language Processing Approach,” in 2nd International Conference on Advancements in Computing (ICAC), IEEE, 2020, pp. 386-391. https://doi.org/10.1109/ICAC51239.2020.9357156DOI
  22. 22.H. Shi, et al., “RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation,” International Journal of Machine Learning and Cybernetics, vol. 15, p. 91, 2022. https://doi.org/10.1007/s44196-022-00155-9DOI
  23. 23.M. Fu, et al., “A Novel Deep Learning-Based Collaborative Filtering Model for Recommendation System,” IEEE Transactions on Cybernetics, vol. 49, no. 3, pp. 1084-1096, 2019. https://doi.org/10.1109/TCYB.2018.2795041DOI
  24. 24.“Deep Learning-Based Multi-Criteria Recommender System for Technology-Enhanced Learning,” Scientific Reports, 2025. https://doi.org/10.1038/s41598-025-97407-3DOI
  25. 25.Y. Di, et al., “Personalized Consumer Federated Recommender System using Fine-Grained Transformation and Hybrid Information Sharing,” IEEE Transactions on Consumer Electronics, 2025. https://doi.org/10.1109/TCE.2025.3526427DOI
  26. 26.“Consumption and Performance: Understanding Longitudinal Dynamics of Recommender Systems via an Agent-Based Simulation Framework,” Information Systems Research, vol. 31, no. 1, pp. 76-101, 2020. https://doi.org/10.1287/isre.2019.0876DOI
Download PDF
Cite This Article
Bayracı, S., Öztürk, U. B., Bilgin, T. T. (2025). A Temporal-Weighted Hybrid Recommender for B2B Vehicle Auctions Using Word2Vec Embeddings. *The European Journal of Research and Development*, 5(1), 540-566. https://doi.org/10.56038/ejrnd.v5i1.718

Bibliographic Info

JournalThe European Journal of Research and Development
Volume5
Issue1
Pages540–566
PublishedDecember 19, 2025
eISSN2822-2296