• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 人工智能与数据挖掘 • 上一篇    下一篇

基于改进CNN的局部相似性预测推荐模型

吴国栋1,2,宋福根1,涂立静2,史明哲2   

  1. (1.东华大学管理学院,上海 200051;2.安徽农业大学信息与计算机学院,安徽 合肥 230036)
  • 收稿日期:2018-06-25 修回日期:2018-11-30 出版日期:2019-06-25
  • 基金资助:

    国家自然科学基金(31671589);安徽省科技攻关重点项目(1501031082)

A local similarity prediction recommendation
model based on improved CNN
 

WU Guodong1,2,SONG Fugen1,TU Lijing2,SHI Mingzhe2   

  1. (1.School of Business and Management,Donghua University,Shanghai 200051;
    2.School of Information and Computer,Anhui Agricultural University,Hefei 230036,China)
     

     
  • Received:2018-06-25 Revised:2018-11-30 Online:2019-06-25

摘要:

为缓解推荐系统中数据稀疏性问题,利用卷积神经网络CNN具有较强捕捉局部特征能力的优势,通过加入一个调节层,提出一种改进CNN的局部相似性预测推荐模型LSPCNN。新模型对初始用户项目评分矩阵进行迭代调整,使用户兴趣偏好局部特征化,再融合CNN对缺失评分进行预测,从而实施个性化推荐。实验结果表明,LSPCNN模型在不同数据稀疏度下的MAE值较传统推荐方法平均下降4%,有效缓解了数据稀疏性,提高了推荐系统的性能。
 

关键词: 卷积神经网络(CNN), 局部相似性, 稀疏性, 推荐系统

Abstract:

In order to alleviate the problem of data sparsity in recommendation systems, based on the advantage of convolutional neural networks (CNNs) in capturing local features, we propose a local similarity prediction recommendation model based on improved CNN (LSPCNN) by adding an adjustment layer. The new model iteratively adjusts the initial user-item scoring matrix to localize user’s interest preference. And then CNNs are integrated to predict the missing score and achieve personalized recommendation. Experimental results show that the MAE value of the LSPCNN model under different degrees of data sparsity decreases by an average of 4% compared with the traditional recommendation methods, and it effectively alleviates the data sparsity problem and improves the performance of recommendation systems.
 
 
 

Key words: convolutional neural network (CNN), local similarity, sparsity, recommender system