方法对比

	Matthews Correlation Coefficient	平衡准确率	F1分数
领域	模型评估	模型评估	模型评估
方法族	MCDM	MCDM	MCDM
起源年份	1975	2010	1979
提出者	Brian W. Matthews	Brodersen, Ong, Stephan, and Buhmann	C. J. van Rijsbergen
类型	Evaluation metric	Evaluation metric	Evaluation metric
开创性文献	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.	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.	van Rijsbergen, C. J. (1979). Information Retrieval (2nd ed.). Butterworth-Heinemann.
别名	Phi Coefficient, Binary Classification Correlation	Average Recall, Equal-weight Average Sensitivity	F-measure, Harmonic Mean
相关	5	5	5
摘要	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.	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.	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.