推荐系统是互联网产品的核心。本文介绍主流推荐算法。 ## 协同过滤 ```python from sklearn.metrics.pairwise import cosine_similarity user_similarity = cosine_similarity(user_item_matrix.fillna(0)) ``` ## 矩阵分解 ```python from scipy.sparse.linalg import svds U, sigma, Vt = svds(R, k=50) predicted_ratings = np.dot(np.dot(U, np.diag(sigma)), Vt) ``` ## 深度学习推荐 ```python class NeuralCF(nn.Module): def __init__(self, num_users, num_items, dim=64): self.user_embedding = nn.Embedding(num_users, dim) self.item_embedding = nn.Embedding(num_items, dim) self.mlp = nn.Sequential( nn.Linear(dim * 2, 128), nn.ReLU(), nn.Linear(128, 1), ) ``` 推荐系统的核心：理解用户意图，平衡探索与利用。