首页|跨境电商下基于商品属性-情境的推荐算法

跨境电商下基于商品属性-情境的推荐算法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
在传统协同过滤推荐算法的基础上,结合跨境电商行业特点,提出了一种基于商品属性和情境权重的混合推荐算法.首先,根据用户商品的历史购买金额和购买次数生成用户偏好评分,并结合用户商品属性相似度和情境化用户相似度得到目标用户的最近邻集,最后将通过变异系数法得到的情境权重纳入评分预测当中,进而生成推荐结果.实证分析表明,本算法能有效提升商品推荐结果的预测准确度,相较基于商品属性的协同过滤推荐算法,本算法可降低商品预测评分平均绝对误差平均达2.72％,提高了跨境电商商品推荐效果.本研究为推荐系统在跨境电商领域的应用提供了新方法.
Recommendation algorithm based on commodity attributes-context under cross-border e-commerce
Based on the traditional collaborative filtering recommendation algorithm and the characteristics of the cross-border e-commerce industry,this paper proposes a hybrid recommendation algorithm based on commodity attributes and context weights.First,user scores are generated based on user's historical purchase amount and frequency.Then,user product attribute similarity and context user similarity are combined to obtain the user's nearest neighbor set.Finally,the context weight is incorporated into the score prediction to get the recommendation results.The results show that this algorithm effectively improves the prediction accuracy of the product recommendation results.Compared to the collaborative filtering algorithm based on commodity attributes,the recommendation algorithm proposed can reduce the average absolute error of the product prediction score by 2.72％on average,thus improving the efficiency of cross-border e-commerce product recommendations.The research provides a new method for the application of recommendation systems in the field of cross-border e-commerce.

cross-border e-commercecollaborative filteringrecommendation systemcommodity attributescontext weight

李建斌、钱自顺、蔡学媛、戴宾

展开 >

华中科技大学管理学院,湖北武汉 430074

武汉纺织大学管理学院,湖北武汉 430200

武汉大学经济管理学院,湖北武汉 430072

跨境电商 协同过滤 推荐系统 商品属性 情境权重

国家自然科学基金资助项目国家自然科学基金资助项目国家自然科学基金资助项目国家自然科学基金资助项目华中科技大学人文社科培育资助项目湖北省普通高校人文社科重点研究基地资助项目

718310077207108572101192721711782021WKFZZX008DSS20210405

2024

10.13383/j.cnki.jse.2024.03.002

系统工程学报
中国系统工程学会

系统工程学报

CSTPCD北大核心
影响因子：1.192
ISSN：1000-5781
年,卷(期)：2024.39(3)