Strategies for learning in class imbalance problems
Strategies for learning in class imbalance problems
复制标题
DOI：
10.1016/s0031-3203(02)00257-1
复制
发表时间：
2003-03-01
影响因子：
8
通讯作者：
Rangel, E
中科院分区：
文献类型：
--
作者：
Barandela, R;Sánchez, JS;Rangel, E
如果一组样本或训练集（TS）中的一个类与其他类相比由非常少量的案例表示，则称其为不平衡的。按照通常的做法[1，2]，我们只考虑两类问题，因此，例子要么是正面的，要么是负面的（即，要么来自少数类，要么来自多数类）。高度不平衡发生在分类器要检测罕见但重要的情况的应用中，例如欺诈性电话、卫星图像中的石油泄漏、制造过程中的故障或罕见的医疗诊断。已经观察到，类不平衡可能导致通过标准监督方法可获得的性能的显著恶化。处理这个问题的大多数尝试可以分为三类[2]。一种是为分类错误分配不同的成本。第二种是通过对少数类进行过采样和/或对多数类进行欠采样来对原始TS进行重新采样，直到类被近似相等地表示。第三个是在内部偏向基于歧视的过程，以弥补阶级不平衡。正如许多作者所指出的那样，分类器在具有类不平衡的应用中的性能不能用平均准确率来表示。例如，考虑一个只有2%的例子是积极的领域。在这种情况下，将所有新样本标记为阴性将提供98%的准确性，但在所有阳性情况下失败。在不平衡的环境中，
A set of examples or training set (TS) is said to be imbalanced if one of the classes is represented by a very small number of cases compared to the other classes. Following the common practice [1, 2], we consider only two-class problems and therefore, the examples are either positive or negative (that is, either from the minority class or the majority class, respectively). High imbalance occur in applications where the classifier is to detect a rare but important case, such as fraudulent telephone calls, oil spills in satellite images, failures in a manufacturing process, or a rare medical diagnoses. It has been observed that class imbalance may cause a significant deterioration in the performance attainable by standard supervised methods. Most of the attempts at dealing with this problem can be grouped into three categories [2]. One is to assign distinct costs to the classification errors. The second is to resample the original TS, either by over-sampling the minority class and/or under-sampling the majority class until the classes are approximately equally represented. The third consists in internally biasing the discrimination-based process so as to compensate for the class imbalance. As pointed out by many authors, the performance of a classifier in applications with class imbalance must not be expressed in terms of the average accuracy. For instance, consider a domain where only 2% examples are positive. In such a situation, labeling all new samples as negative would give an accuracy of 98%, but failing on all positive cases. Consequently, in environments with imbalanced