Evaluation Measures of the Classification Performance of Imbalanced Data Sets

摘要

Discriminant Measures for Classification Performance play a critical role in guiding the design of classifiers, assessment methods and evaluation measures are at least as important as algorithm and are the first key stage to a successful data mining. We systematically summarized the evaluation measures of Imbalanced Data Sets (IDS). Several different type measures, such as commonly performance evaluation measures and visualizing classifier performance measures have been analyzed and compared. The problems of these measures towards IDS may lead to misunderstanding of classification results and even wrong strategy decision. Beside that, a series of complex numerical evaluation measures were also investigated which can also serve for evaluating classification performance of IDS.