摘要
协同过滤推荐算法是最经典、应用最成功的推荐算法之一,但该算法在数据稀疏性、冷启动和时间因素等方面还存在一定问题,于是,提出一种基于柯西分布量子粒子群的混合推荐算法。该算法首先构建基于时间因子的混合推荐模型,再利用柯西分布量子粒子群算法搜索模型中的最优参数组合,其中,混合推荐模型通过把用户和项目的属性信息添加到协同过滤推荐算法中,并引入能够代表用户兴趣迁移特性的时间因子构建而成。最后,与人工蜂群算法(ABC)以及基本粒子群算法(PSO)进行比较。研究结果表明:在提高推荐准确度、缓解数据稀疏性以及冷启动等方面,本文提出的算法优于其他算法。
Collaborative filtering recommendation algorithm is one of the most typical and successful technologies, about exist problems such as data sparsity, cold start and time factor. Therefore, a hybrid recommendation algorithm based on Cauchy quantum-behaved particle swarm optimization was proposed. According to the algorithm, the hybrid recommendation model was constructed based on time factor, and then, the Cauchy quantum-behaved particle swarm optimization algorithm was applied for searching the optimal parameters of the model. The hybrid recommender model was built by adding the features of the users and items to the traditional collaborative filtering algorithm and introducing a time factor represented the change of users＇ interests. The algorithm proposed in this paper was compared with the artificial bee colony（ABC） and particle swarm optimization（PSO）. The results show that in increasing recommendation accuracy and alleviating the data sparsity and cold start, the proposed algorithm is better than other algorithms.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2015年第8期2898-2905,共8页
Journal of Central South University:Science and Technology
基金
国家自然科学基金资助项目(61102105)
黑龙江省博士后出站启动基金资助项目(LBH-Q12117)
教育部博士点基金资助项目(20102304120014)
黑龙江省自然科学基金资助项目(F201029)~~
关键词
推荐算法
柯西分布量子粒子群
数据稀疏
冷启动
时间因子
recommendation algorithm
Cauchy quantum-behaved particle swarm optimization
data sparseness
cold start
time factor
