针对新电影的冷启动问题提出一种基于BP神经网络的协同过滤推荐算法（IW-CFW），该算法将电影相似性采 用BP神经网络进行融合，根据预测评分和真实评分之间的误差对BP网络模型进行优化调整，得到最终的预测模型。通过比 较该算法和其他三种算法在MovieLens和Movie-Little数据集上的平均绝对误差（MAE）和均方根误差（RMSE），实验结果证 明该算法能有效解决新电影的冷启动问题，并能产生更准确的推荐结果。

To solve the cold start problem of new movies, a collaborative filtering recommendation algorithm (IW-CFW) based on BP neural network is proposed. In this algorithm, the similarity of movies is fused by BP neural network, and the BP network model is optimized and adjusted according to the error between the predicted score and the true score, and the final prediction model is obtained. By comparing the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the proposed algorithm with the other three algorithms on the Movielens and Movie-little datasets, the experimental results show that the proposed algorithm can effectively solve the cold start problem of new movies and produce more accurate recommendation results.