方法对比

	平衡准确率	准确率	F1分数	Matthews Correlation Coefficient
领域	模型评估	模型评估	模型评估	模型评估
方法族	MCDM	MCDM	MCDM	MCDM
起源年份	2010	20th century	1979	1975
提出者	Brodersen, Ong, Stephan, and Buhmann	Historical statistical foundations	C. J. van Rijsbergen	Brian W. Matthews
类型	Evaluation metric	Evaluation metric	Evaluation metric	Evaluation metric
开创性文献	Brodersen, K. H., Ong, C. S., Stephan, K. E., & Buhmann, J. M. (2010). The balanced accuracy and its posterior distribution. 20th International Conference on Pattern Recognition (ICPR), 3121-3124.	Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861-874.	van Rijsbergen, C. J. (1979). Information Retrieval (2nd ed.). Butterworth-Heinemann.	Matthews, B. W. (1975). Comparison of predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA)-Protein Structure, 405(2), 442-451.
别名	Average Recall, Equal-weight Average Sensitivity	Overall Accuracy, Correct Classification Rate	F-measure, Harmonic Mean	Phi Coefficient, Binary Classification Correlation
相关	5	5	5	5
摘要	Balanced accuracy is the average of recall values computed for each class separately. It corrects for class imbalance by giving equal weight to the performance on each class, regardless of class frequency in the dataset.	Accuracy is the proportion of correct predictions among the total number of predictions made by a classification model. It is the most intuitive performance metric and measures how often the classifier makes correct predictions overall, regardless of class.	The F1-score is the harmonic mean of precision and recall, providing a single metric that balances both concerns. It was introduced by van Rijsbergen in information retrieval and has become a standard metric for evaluating classification models where both precision and recall are important.	The Matthews Correlation Coefficient (MCC) is a correlation measure between predicted and actual binary classifications. It ranges from -1 to 1 and is considered one of the most reliable single-score metrics for evaluating binary classifiers, especially on imbalanced datasets.