用户真实的购买场景中,购物不仅仅看兴趣,当下以及未来需求也很重要,而现有大部分推荐方法研究的是挖掘用户近期兴趣,较少从商品间的关系来研究用户潜在需求.为了提高推荐算法准确性,丰富推荐种类,本文将商品互补替代关系特征和购买先后序列模式融入到推荐算法中,提出一种考虑商品互补替代关系和购买序列模式来研究用户潜在需求的推荐算法,该算法在亚马逊公开数据集Grocery上进行验证,并与相关算法进行对比,结果表明所提算法在命中率HR(hits ratio)和归一化折损累计增益NDCG(normalized discounted cumulative gain)指标上均得到有效的改进.
In the real purchasing scenario of users, shopping is not only based on interests, but also on current and future needs. However, most of the existing recommendation methods focus on mining users recent interests, and rarely study users potential needs from the relationship between products. In order to improve the accuracy of the recommendation algorithm and enrich the types of recommendation, this paper integrates the characteristics of commodity complementary substitution relationship and purchase sequence pattern into the recommendation algorithm, and proposes a recommendation algorithm that considers the commodity complementary substitution relationship and purchase sequence pattern to study the potential needs of users. The algorithm is verified on Amazon public data set Grocery. Compared with the relevant algorithms, the results show that the proposed algorithm is effectively improved in hits Ratio HR(hits ratio)and normalized discounted cumulative gain(NDCG).
[1] 姜久雷,潘姿屹,李盛庆.融合信任度的神经网络推荐算法[J].计算机应用与软件, 2023, 40(8): 274-282, 311. DOI: 10.3969/j.issn.1000-386x.2023.08.043.
[2] 冯兴杰,生晓宇.基于图神经网络与深度学习的商品推荐算法[J].计算机应用研究, 2021, 38(12): 3617-3622. DOI: 10.19734/j.issn.1001-3695.2021.05.0183
[3] 于健,赵满坤,高洁,等.基于高阶和时序特征的图神经网络社会化推荐算法研究[J].计算机科学, 2023, 50(3): 49-64. DOI: 10.11896/jsjkx.220700108.
[4] HAN J W, PEI J, YIN Y W. Mining frequent patterns without candidate generation[C] //Proceedings of the 2000 ACM SIGMOD international conference on Management of data. Dallas Texas USA. ACM, 2000: 1-12. DOI: 10.1145/342009.335372.
[5] MA Y H, JIA J, ZHOU S P, et al. Towards better understanding the clothing fashion styles: a multimodal deep learning approach[J]. Proc AAAI Conf Artif Intell, 2017, 31(1): 38-44. DOI: 10.1609/aaai.v31i1.10509.
[6] MA W Z, ZHANG M, CAO Y, et al. Jointly learning explainable rules for recommendation with knowledge graph[C] //The World Wide Web Conference. San Francisco CA USA. ACM, 2019: 1210-1221. DOI: 10.1145/3308558.3313607.
[7] MISHRA R, KUMAR P, BHASKER B. A web recommendation system considering sequential information[J]. Decis Support Syst, 2015, 75: 1-10. DOI: 10.1016/j.dss.2015.04.004.
[8] SALEHI M, NAKHAI KAMALABADI I, GHAZNAVI GHOUSHCHI M B. Personalized recommendation of learning material using sequential pattern mining and attribute based collaborative filtering[J]. Educ Inf Technol, 2014, 19(4): 713-735. DOI: 10.1007/s10639-012-9245-5
[9] ZHOU G R, MOU N, FAN Y, et al. Deep interest evolution network for click-through rate prediction[J]. Proc AAAI Conf Artif Intell, 2019, 33(1): 5941-5948. DOI: 10.1609/aaai.v33i01.33015941.
[10] 李杰,杨芳,徐晨曦.考虑时间动态性和序列模式的个性化推荐算法[J].数据分析与知识发现, 2018, 2(7): 72-80. DOI: 10.11925/infotech.2096-3467.2017.0857.
[11] 余皑欣,冯秀芳,孙静宇.结合物品相似性的社交信任推荐算法[J].计算机科学, 2022, 49(5): 144-151. DOI: 10.11896/jsjkx.210300217
[12] BORDES ANTOINE, USUNIER NICOLAS, GARCIA-DURAN ALBERTO, et al. Translating Embeddings for Modeling Multi-relational Data[C] //Advances in neural information processing systems. 2013: 2787-2795.
[13] AGRAWAL R, IMIELIN'SKI T, SWAMI A. Mining association rules between sets of items in large databases[C] //Proceedings of the 1993 ACM SIGMOD international conference on Management of data. Washington D.C. USA. ACM, 1993: 207-216.DOI: 10.1145/170035.170072.
[14] WANG C Y, ZHANG M, MA W Z, et al. Make it a chorus: knowledge- and time-aware item modeling for sequential recommendation[C] //Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Virtual Event China. ACM, 2020: 109-118. DOI: 10.1145/3397271.3401131.
[15] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian personalized ranking from implicit feedback[J]. Proc 25th Conf Uncertain Artif Intell UAI 2009, 2009: 452-461.
[16] WANG C Y, ZHANG M, MA W Z, et al. Modeling item-specific temporal dynamics of repeat consumption for recommender systems[C] //The World Wide Web Conference. San Francisco CA USA. ACM, 2019: 1977–1987. DOI: 10.1145/3308558.3313594.
[17] HE X N, LIAO L Z, ZHANG H W, et al. Neural collaborative filtering[C] //Proceedings of the 26th International Conference on World Wide Web. Perth Australia. Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee, 2017: 173–182. DOI: 10.1145/3038912.3052569.
[18] HIDASI B, KARATZOGLOU A, BALTRUNAS L, et al. Session-based recommendations with recurrent neural networks[EB/OL]. 2015: arXiv: 1511.06939. http://arxiv.org/abs/1511.06939
[19] LOYOLA P, LIU C, HIRATE Y. Modeling user session and intent with an attention-based encoder-decoder architecture[C] //Proceedings of the Eleventh ACM Conference on Recommender Systems. Como Italy. ACM, 2017: 147–151. DOI: 10.1145/3109859.3109917.
[20] ZHANG Y F, AI Q Y, CHEN X, et al. Learning over knowledge-base embeddings for recommendation[J]. arXiv E Prints, 2018: arXiv: 1803.06540. DOI: 10.48550/arXiv.1803.06540
[21] FAN W Q, LI Q, CHENG M. Deep modeling of social relations for recommendation[J]. Proc AAAI Conf Artif Intell, 2018, 32(1): 1-5. DOI: 10.1609/aaai.v32i1.12132. (
