Collaborative filtering recommendation algorithm based on KNN and Xgboost hybrid

Abstract In the traditional collaborative filtering recommendation algorithm, it is easy to fall into the dilemma of local optimization due to single classification, which affects the recommendation effect of the algorithm. A hybrid collaborative filtering recommendation algorithm based on KNN-Xgboost is proposed. The algorithm uses KNN to fill in the user’s predictive evaluation with less project evaluation, reducing the sparseness of the matrix. Then the Xgboost algorithm is used to implement multi-classifiers to predict the data, and the multi-class calculation results are calculated to form the recommended results. The experimental results show that the sparseness of the matrix is solved to a certain extent, and the recommendation accuracy is improved.