灰狼优化支持向量机的推荐算法

Recommendation algorithm of grey wolf optimized support vector machine

针对推荐系统中用户项目评分矩阵稀疏性和冷启动问题,采用灰狼算法(GWO)优化支持向量机(SVM)分类器,二者相结合,提出一种新算法.利用卷积矩阵分解模型(Conv MF)提取用户-项目数据的有效特征向量,降低维数,形成样本集.再将样本集用于向量机的分类识别,对错分点进行自动检测,通过灰狼算法迭代更新,找出全局最优值,从而可以根据用户行为分配不同特征的相应产品.研究结果表明:灰狼算法优化支持向量机比传统的网格搜索算法(GS)、粒子群优化算法(PSO)等得到的分类模型能更准确、有效地对推荐结果进行优化识别,降低错误率,提高预测精度和推荐准确率.

Aiming at the sparsity and cold start of user item score matrix in the recommendation system,a new algorithm is proposed by using the gray wolf algorithm(GWO)to optimize the support vector machine(SVM)classifier.Convolution matrix factorization model(ConvMF)is used to extract the effective feature vector of the user-item data,reduce the dimensionality,and form a sample set.Then the sample set is used for the classification and recognition of the vector machine,and the error points are automatically detected,and the gray wolf algorithm is updated iteratively to find the global optimal value,so that the corresponding products with different characteristics can be assigned according to user behavior.The study results show that the gray wolf algorithm optimized support vector machine is better than the traditional grid search algorithm(GS),particle swarm optimization algorithm(PSO)and other classification models.It can more accurately and effectively optimize the identification of recommendation results,reduce the error rate,and improve the prediction accuracy and recommendation accuracy.