基于DE蝙蝠算法的混合推荐模型设计  

Design of Hybrid Recommendation Model Based on DE Bat Algorithm

作　　者：何昌隆 文斌[1] HE Changlong;WEN Bin(College of Communication Engineering,Chengdu University of Information Technology,Chengdu 610225)

机构地区：[1]成都信息工程大学通信工程学院,成都610225

出　　处：《计算机与数字工程》2022年第7期1439-1443,共5页Computer & Digital Engineering

摘　　要：针对单一推荐算法的精度不足以及数据稀疏问题,普通加权混合推荐模型权值难以收敛到全局最优的问题,提出了一种基于差分进化蝙蝠算法构建的多元加权混合推荐模型(DEBA-Hybrid Recommendation Model)。该模型通过差分进化蝙蝠算法优秀的全局寻优能力来寻找到适当的权值,对多种主流的推荐算法进行加权融合,以生成最终的用户评分预测矩阵进行物品推荐。使用RMSE和MAE指标在Movielens公开数据集上进行模型评估,结果表明该模型对比单一推荐算法和传统的加权混合推荐模型在推荐效果上有明显提升,具有实际意义。Aiming at the problem of insufficient accuracy of the single recommendation algorithm and data sparseness,the weight of the ordinary weighted hybrid recommendation model is difficult to converge to the global optimal problem.A multi-weight⁃ed hybrid recommendation model based on the differential evolution bat algorithm(DEBA-Hybrid Recommendation Model)is pro⁃posed.The model uses the excellent global optimization ability of the differential evolution bat algorithm to find appropriate weights,and performs weighted fusion on a variety of mainstream recommendation algorithms to generate a final user rating prediction matrix for item recommendation.RMSE and MAE indicators are used to evaluate the model on the Movielens public data set,the results show that the model has a significant improvement in recommendation effect compared with the single recommendation algorithm and the traditional weighted mixed recommendation model,and has practical significance.

关 键 词：混合推荐模型 蝙蝠算法 差分进化 推荐算法 协同过滤 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]