{
    "api": "YAML JSON TOON Database",
    "version": "1.0.0",
    "format": "json",
    "dataset": {
        "id": 14,
        "slug": "ml-evaluation-metrics",
        "title": "Machine Learning Evaluation Metrics",
        "description": "Common ML evaluation metrics: Accuracy, Precision, Recall, F1 Score, ROC-AUC, MAE, MSE, and R-squared with formulas and best-use scenarios.",
        "summary": "Evaluation metrics for machine-learning models with type, formula, best use and range: accuracy, precision, recall, F1, ROC-AUC, MAE, MSE and R-squared, extended with specificity, log loss, RMSE, Matthews correlation, IoU, perplexity, BLEU, nDCG and Cohen's kappa.",
        "use_when": [
            "You need the formula and interpretation of a metric.",
            "You are choosing a metric for imbalanced classification, ranking or generation."
        ],
        "caveats": [
            "A single metric hides trade-offs; report several and choose by the cost of different errors.",
            "Metrics such as BLEU correlate imperfectly with human judgment of quality.",
            "ROC-AUC can range from 0 to 1; 0.5 is a random ranking, not the lower bound. Report prevalence and the decision threshold alongside threshold-specific metrics."
        ],
        "related": [
            "statistics-basics",
            "ai-ethics-interpretability",
            "regularization-techniques",
            "llm-glossary",
            "rag-retrieval-metrics",
            "experimental-design-pitfalls"
        ],
        "category": "AI & ML Terms",
        "category_slug": "ai-ml-terms",
        "tags": "ml,evaluation,metrics,data science",
        "view_count": 0,
        "created_at": 1777673262,
        "updated_at": 1791799373,
        "sources": [
            {
                "title": "scikit-learn model evaluation",
                "url": "https://scikit-learn.org/stable/modules/model_evaluation.html"
            }
        ],
        "reading": [
            "evaluate-rag-retrieval-before-generation"
        ],
        "reviewed_at": "2026-10-12",
        "provenance": "Original editorial reference notes by YJTOON, informed by the linked primary documentation. External specifications retain their own licenses.",
        "entry_count": 21,
        "fields": [
            {
                "section": "metrics",
                "field": "name",
                "type": "string",
                "example": "Accuracy"
            },
            {
                "section": "metrics",
                "field": "type",
                "type": "string",
                "example": "Classification"
            },
            {
                "section": "metrics",
                "field": "formula",
                "type": "string",
                "example": "(TP + TN) / (TP + TN + FP + FN)"
            },
            {
                "section": "metrics",
                "field": "best_for",
                "type": "string",
                "example": "Balanced datasets"
            },
            {
                "section": "metrics",
                "field": "range",
                "type": "string",
                "example": "[0, 1], higher is better"
            }
        ]
    },
    "data": {
        "metrics": [
            {
                "name": "Accuracy",
                "type": "Classification",
                "formula": "(TP + TN) / (TP + TN + FP + FN)",
                "best_for": "Balanced datasets",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "Precision",
                "type": "Classification",
                "formula": "TP / (TP + FP)",
                "best_for": "Minimizing false positives",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "Recall",
                "type": "Classification",
                "formula": "TP / (TP + FN)",
                "best_for": "Minimizing false negatives",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "F1 Score",
                "type": "Classification",
                "formula": "2 * (Precision * Recall) / (Precision + Recall)",
                "best_for": "Imbalanced datasets",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "ROC-AUC",
                "type": "Classification",
                "formula": "Area under ROC curve",
                "best_for": "Ranking quality",
                "range": "[0, 1]; 0.5 is the random-ranking baseline, and lower values are possible"
            },
            {
                "name": "MAE",
                "type": "Regression",
                "formula": "mean(|y_true - y_pred|)",
                "best_for": "Average error magnitude",
                "range": "[0, inf), lower is better"
            },
            {
                "name": "MSE",
                "type": "Regression",
                "formula": "mean((y_true - y_pred)^2)",
                "best_for": "Penalizing large errors",
                "range": "[0, inf), lower is better"
            },
            {
                "name": "R-squared",
                "type": "Regression",
                "formula": "1 - (SS_res / SS_tot)",
                "best_for": "Proportion of variance explained",
                "range": "(-inf, 1], higher is better"
            },
            {
                "name": "Specificity",
                "type": "Classification",
                "formula": "TN / (TN + FP)",
                "best_for": "Measuring how well negatives are identified",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "Log Loss",
                "type": "Classification",
                "formula": "-(1/N) * sum(y log p + (1 - y) log(1 - p))",
                "best_for": "Evaluating predicted probabilities",
                "range": "[0, infinity), lower is better"
            },
            {
                "name": "Matthews Correlation Coefficient",
                "type": "Classification",
                "formula": "(TP*TN - FP*FN) / sqrt((TP+FP)(TP+FN)(TN+FP)(TN+FN))",
                "best_for": "Imbalanced binary classification",
                "range": "[-1, 1], higher is better"
            },
            {
                "name": "RMSE",
                "type": "Regression",
                "formula": "sqrt(mean((y - y_hat)^2))",
                "best_for": "Regression where large errors should weigh more, in the units of the target",
                "range": "[0, infinity), lower is better"
            },
            {
                "name": "Intersection over Union",
                "type": "Detection and segmentation",
                "formula": "|A intersect B| / |A union B|",
                "best_for": "Overlap between predicted and true regions",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "Perplexity",
                "type": "Language modeling",
                "formula": "exp(-(1/N) * sum(log p(w_i | context)))",
                "best_for": "Comparing language models on the same text",
                "range": "[1, infinity), lower is better"
            },
            {
                "name": "BLEU",
                "type": "Machine translation",
                "formula": "Brevity penalty * geometric mean of n-gram precisions",
                "best_for": "Comparing translations with references",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "nDCG",
                "type": "Ranking",
                "formula": "DCG / ideal DCG",
                "best_for": "Search and recommendation quality with graded relevance",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "Cohen's Kappa",
                "type": "Agreement",
                "formula": "(p_o - p_e) / (1 - p_e)",
                "best_for": "Agreement between annotators beyond chance",
                "range": "[-1, 1], higher is better"
            },
            {
                "name": "Average Precision",
                "type": "Ranking / binary classification",
                "formula": "sum((recall_n - recall_previous) * precision_n)",
                "best_for": "Summarizing the precision-recall tradeoff when positives are rare",
                "range": "[0, 1], higher is better; prevalence affects the baseline"
            },
            {
                "name": "Brier Score (binary)",
                "type": "Probability prediction",
                "formula": "mean((p_positive - y_binary)^2)",
                "best_for": "Evaluating probabilistic predictions alongside calibration plots",
                "range": "[0, 1], lower is better"
            },
            {
                "name": "Balanced Accuracy",
                "type": "Classification",
                "formula": "mean(recall_per_class)",
                "best_for": "Giving each class equal weight in the recall average",
                "range": "[0, 1], higher is better"
            },
            {
                "name": "Pinball Loss",
                "type": "Quantile regression",
                "formula": "mean(max(q * error, (q - 1) * error)); error = y_true - y_pred",
                "best_for": "Evaluating a specified conditional quantile",
                "range": "[0, inf), lower is better"
            }
        ]
    }
}