Cross-domain collaborative filtering (CDCF) solves the sparsity problem by transferring rating knowledge fromauxiliary domains.\nObviously, different auxiliary domains have different importance to the target domain. However, previous works cannot evaluate\neffectively the significance of different auxiliary domains. To overcome this drawback, we propose a cross-domain collaborative\nfiltering algorithm based on Feature Construction and LocallyWeighted Linear Regression (FCLWLR).We first construct features\nin different domains and use these features to represent different auxiliary domains.Thus the weight computation across different\ndomains can be converted as the weight computation across different features. Then we combine the features in the target domain\nand in the auxiliary domains together and convert the cross-domain recommendation problem into a regression problem. Finally,\nwe employ a Locally Weighted Linear Regression (LWLR) model to solve the regression problem. As LWLR is a nonparametric\nregression method, it can effectively avoid underfitting or overfitting problem occurring in parametric regression methods. We\nconduct extensive experiments to show that the proposed FCLWLR algorithm is effective in addressing the data sparsity problem\nby transferring the useful knowledge from the auxiliary domains, as compared to many state-of-the-art single-domain or crossdomain\nCF methods.
Loading....