A customer avatar model based on Kolmogorov–Arnold networks
Abstract
The increasing pace of development of e-commerce continues to present new challenges in terms of personalizing product search and recommendations. Monolithic search and recommendation systems have become cumbersome and are unable to effectively address the need for a deeper understanding of users on electronic trading platforms (ETPs) despite having access to comprehensive information about their interests and purchase histories. Collaborative filtering mechanisms which are widely used suffer from a lack of diversity in offerings and a reduced capacity to surprise users. Additionally, the low frequency of recommendation updates and the replacement of “personalized” with “similar to others” concepts contribute to these issues. We have approached the resolution of these issues by developing a shopping assistant named “Ellochka” that is individual for each user of ETP. The digital avatar model of the user continually searches for relevant products based on their history of interaction with ETP. We were guided by the principle of independence – avatar models do not share information with each other. When a new user joins, they are assigned a unique avatar model that evolves independently. Each avatar has its own language to generate search queries. The level of complexity of each avatar can vary depending on the intensity of its interaction with ETP. Continued interaction with the avatar allows for tracking of optimal purchase conditions, reminding users of expiration dates and the need for re-purchasing frequently purchased items. Isolating the avatar allows it to be retrained after each event, without significantly impacting the overall search and recommendation system. The use of neural network architecture-based and Kolmogorov–Arnold networks in the avatar-model has led to improvements in the main indicators of search and recommendation effectiveness, namely, novelty and diversity.
Downloads
References
Butorin A.V., Murtazin D.G., Krasnov F.V. (2020) Method and system for predicting effective thicknesses in the interwell space when constructing a geological model based on the method of clustering spectral curves. Patent for invention RU 2718135 C1, 03/30/2020. Application No. 2019128334 dated 09/09/2019.
Krasnov F. (2023) Query understanding via Language Models based on transformers for e-commerce. International Journal of Open Information Technologies, vol. 11, no. 9, pp. 33–40 (in Russian).
Muennighoff N., Tazi N., Magne L., Reimers N. (2022) MTEB: Massive text embedding benchmark. arXiv:2210.07316. https://doi.org/10.48550/arXiv.2210.07316
Li P., Tuzhilin A. (2023) When variety seeking meets unexpectedness: Incorporating variety-seeking behaviors into design of unexpected recommender systems. Information Systems Research, vol. 35, no. 3. https://doi.org/10.1287/isre.2021.0053
Wang Y., Banerjee C., Chucri S., et al. (2024) Beyond item dissimilarities: Diversifying by intent in recommender systems. arXiv:2405.12327. https://doi.org/10.48550/arXiv.2405.12327
Castells P., Hurley N., Vargas S. (2022) Novelty and diversity in recommender systems. Recommender Systems Handbook (eds. F. Ricci, L. Rokach, B. Shapira). Springer, New York, NY, pp. 603–646. https://doi.org/10.1007/978-1-0716-2197-4_16
Ding Q., Liu Y., Miao C., et al. (2021) A hybrid bandit framework for diversified recommendation. Proceedings of the AAAI conference on artificial intelligence, vol. 35, no. 5, pp. 4036–4044. https://doi.org/10.1609/aaai.v35i5.16524
Li J., Wang M., Li J., et al. (2023) Text is all you need: Learning language representations for sequential recommendation. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1258–1267. https:// doi.org/10.1145/3580305.3599519
Sun F., Liu J., Wu J., et al. (2019) BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. Proceedings of the 28th ACM international conference on information and knowledge management, pp. 1441–1450. https://doi.org/10.1145/3357384.3357895
Klenitskiy A., Vasilev A. (2023) Turning dross into gold loss: is BERT4Rec really better than SASRec? Proceedings of the 17th ACM Conference on Recommender Systems, pp. 1120–1125.
Ji Z., Yu T., Xu Y., et al. (2023) Towards mitigating LLM hallucination via self reflection. Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 1827–1843.
Egorov E.A., Rogachev A.I. (2023) Adaptive spectral normalization for generative models. Doklady Mathematics, vol. 108(suppl. 2), pp. S205–S214. https://doi.org/10.1134/S1064562423701089
Chang W.C., Jiang D., Yu H.F., et al. (2021) Extreme multi-label learning for semantic matching in product search. Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, pp. 2643–2651.
Sennrich R., Haddow B., Birch A. (2016) Neural machine translation of rare words with subword units. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 1715–1725. https://doi.org/10.18653/v1/P16-1162
Kudo T., Richardson J. (2018) SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 66–71.
Liu Z., Wang Y., Vaidya S., et al. (2024) KAN: Kolmogorov-Arnold networks. arXiv:2404.19756. https://doi.org/10.48550/arXiv.2404.19756
Vaca-Rubio C. J., Blanco L., Pereira R., Caus M. (2024) Kolmogorov-Arnold networks (KANs) for time series analysis. arXiv:2405.08790. https://doi.org/10.48550/arXiv.2405.08790
Ma X., Gong Y., He P., et al. (2023) Query rewriting for retrieval-augmented Large Language Models. arXiv:2305.14283. https://doi.org/10.48550/arXiv.2305.14283
Chen Z., Fan X., Ling Y. (2020) Pre-training for query rewriting in a spoken language understanding system. ICASSP 2020 – 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 7969–7973. https://doi.org/10.1109/ICASSP40776.2020.9053531
Bhandari M., Wang M., Poliannikov O., Shimizu K. (2023) RecQR: Using Recommendation Systems for Query Reformulation to correct unseen errors in spoken dialog systems. 17th ACM Conference on Recommender Systems (RecSys’23), Singapore, pp. 1019–1022.
Kim T.H., Neubauer M., Sfiligoi I., et al. (2004) The CDF central analysis farm. IEEE Transactions on Nuclear Science, vol. 51, no. 3, pp. 892–896. https://doi.org/10.1109/TNS.2004.829574
Kuleshov A.P. (2008) Cognitive technologies in adaptive models of complex objects. Informatsionnye Tekhnologii i Vychslitel'nye Sistemy, vol. 1, pp. 18–29.
Luo C., Lakshman V., Shrivastavaet A., et al. (2022) ROSE: Robust caches for Amazon product search. WWW '22: Companion Proceedings of the Web Conference 2022, pp. 89–93. https://doi.org/10.1145/3487553.3524213
