选择偏最小二乘的最佳区间，提高预测精度，减小计算量-interval least Least Squares to reduce the computational work while keeping higher predictive accuracy

等渗的插图对生成的数据回归。等张回归发现引入近似函数的同时最小化均方误差的训练数据。-An illustration of the isotonic regression on generated data. The isotonic regression finds a non-decreasing approximation of a function while minimizing the mean squared error on the training data.

利用SVD实现item-based CF: 优点： 简化数据，去除噪声，提高算法的结果 缺点： 数据的转换可能难以理解 适用数据类型： 数值型数据(Svd decomposition plays an important role in the decomposition of eigenvalues of high-dimensional data, while using low-dimensional data for approximate approximation)