首页|微观行为洞察下电商用户多周期购买兴趣的融合表征

微观行为洞察下电商用户多周期购买兴趣的融合表征

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
电子商务是数字经济产业中的重要应用领域.在电商平台中用户与商品的交互会话中,微观操作行为可以洞察用户细粒度的兴趣偏好.同时,宏观的多周期会话序列又可以反映用户兴趣的动态演化.因此,如何融合二者进行准确全面的用户兴趣表征,进而开展精准推荐是当前的一个热点和难点问题.深度循环神经网络RNN在处理周期性和长期依赖关系的序列数据方面具有突出的优势,是当今人工智能AI的核心方法之一.基于此,在本文构建的Mp-UIP模型框架中,首先对用户会话中的微观行为进行细粒度的行为规律与兴趣学习.其次,设计分层的RNN网络结构:会话级LSTMses、区块级LSTMblo和用户级LSTMusr,分别学习用户短期、中期以及长期的兴趣演变,并进行多周期的兴趣融合.最后,在两个实际数据集上,本文设计了模型消融、基准模型对比、稀疏性评价以及实际案例分析四方面的实验.在考察推荐准确性和排名正确性的两个指标:Recall@K和MRR@K上,实验结果验证提出的模型Mp-UIM较现有的经典模型表现最佳.这表明提出的模型Mp-UIP将用户微观操作细节中的兴趣学习与宏观会话序列中的多周期兴趣演化相融合后,能够构建出更加准确全面的用户兴趣模型,服务于精准、个性化的电子商务智能推荐服务.
Fusion representation of multi-period purchase interests of e-commerce user based on insights of micro behaviors
E-commerce is an important application field in the digital economy industry.In the interaction sessions between users and goods on the e-commerce platform,the micro-operation behaviors can gain insight into the user's fine-grained purchase interests,and at the same time,the macro multi-period session sequence can reflect the dynamic evolution of user's interests.Therefore,it has become a hot and difficult problem that how to integrate the two to conduct accurate and comprehensive user interest modeling,and then carry out accurate recommendation.The deep recurrent neural network(RNN)has outstanding advantages in processing serial data with periodic and long-term dependencies,and is one of the core methods of AI.Based on this,a hierarchical RNN network:Session-level LSTMses,block-level LSTMblo and user-level LSTMusr,is designed in the framework of the proposed model MpUIP.Firstly,the user's fine-grained in-terests are first learned from the micro behavior details in the session.Further,the evolution of user's short-term,medium-term and long-term interests are learned,and the multi-period in-terests are fused.Finally,on two real datasets,four experiments:model ablation,benchmark model comparison,sparsity evaluation,and real case analysis are conducted.On the two typical indicators of recommendation:Recall@K and MRR@K,the experimental results verify that the proposed model Mp-UIP has best performance than the existing classical models.This confirms that the model Mp-UIP can indeed build a more accurate and comprehensive user interest model by combining the user's fine-grained interests with the multi-period interest evolution represen-tation,so as to serve for the accurate and personalized E-commerce recommendations.

e-commercemulti-period user interestssession-based recommendationrecurrent neural networkbehavior details

朱志国、孔立平、姜盼、高明、樊卫国

展开 >

东北财经大学管理科学与工程学院,大连 116025

辽宁省大数据管理与优化决策重点实验室,大连 116025

东北财经大学金融学院,大连 116025

美国爱荷华大学商务分析系,爱荷华州52241

展开 >

电子商务 多周期用户兴趣 会话推荐 循环神经网络 行为细节

国家自然科学基金面上项目国家自然科学基金面上项目教育部人文社科规划基金2022年度辽宁省教育厅基本科研面上项目

721720257210105121YJAZH130LJKMZ20221606

2024

10.12011/SETP2023-1198

系统工程理论与实践
中国系统工程学会

系统工程理论与实践

CSTPCDCSSCI北大核心
影响因子：1.575
ISSN：1000-6788
年,卷(期)：2024.44(1)
  • 46