3.12 Choosing the Most Appropriate Metric for the Objective

Key Takeaways

  • Start from the asymmetry of the business costs: whichever error type is more expensive determines whether precision, recall, or a balance is optimised.
  • When false negatives dominate the cost — disease screening, fraud, equipment failure — maximise recall or $F_2$.
  • When false positives dominate — spam filtering, automated account closure, costly interventions — maximise precision or $F_{0.5}$.
  • For rare events, prefer PR-AUC over ROC-AUC and never report raw accuracy; for well-calibrated probabilities used in expected-value decisions, use log loss.
  • For regression, pick RMSE when large errors are disproportionately costly, MAE when cost is proportional to error, and $R^2$ only for communicating explanatory power.
Last updated: August 2026

3.12 Choosing the Most Appropriate Metric for the Objective

Metric selection is not a statistical preference — it is a translation of the business cost structure into a single number the tuning loop can optimise. The exam poses this as a scenario, and the scenario always contains the decisive clue.

The Decision Procedure

  1. Classification or regression? Determined by the target.
  2. What does each error type cost? Write down the cost of a false positive and of a false negative. Whichever is larger is what the metric must punish.
  3. How rare is the positive class? Below roughly 5–10% prevalence, accuracy and ROC-AUC both flatter the model; use PR-AUC and $F_\beta$.
  4. Is a hard decision made, or is the score consumed downstream? A hard decision calls for a threshold metric; a score feeding an expected-value calculation calls for a calibration metric such as log loss.
  5. Is the metric being reported to stakeholders? Prefer one expressed in units they already reason about — dollars, minutes, percentage points.

Scenario to Metric

ScenarioDominant costMetric
Cancer screening: a missed tumour is fatal, a false alarm means one more blood testFalse negativesRecall, or $F_2$
Spam filter: a lost legitimate email is far worse than a spam message getting throughFalse positivesPrecision, or $F_{0.5}$
Fraud detection at 0.2% prevalence, blocking a card costs customer frictionBoth, asymmetricPR-AUC to compare models, $F_\beta$ at the chosen threshold
Credit limit decisions where the score feeds an expected-loss calculationProbability qualityLog loss
Ranking a recommendation slate — only the ordering is usedOrdering qualityROC-AUC or ranking metrics
Balanced classes, symmetric costsNeitherAccuracy or F1
Predicting house prices where a large miss is disproportionately costlyLarge errorsRMSE
Predicting delivery times where cost accrues per minute lateProportionalMAE
Explaining to executives how much of price variation the model capturesCommunication$R^2$
Demand forecasting across products at very different scalesRelative errorSMAPE (MAPE breaks near zero)

Traps

  • Accuracy under imbalance. At 99.8% negatives, "predict negative always" scores 99.8%. Any answer choosing accuracy on a rare-event problem is wrong.
  • ROC-AUC under extreme imbalance. The false-positive-rate denominator is $FP + TN$; with an enormous $TN$, hundreds of false positives barely move it. PR-AUC ignores true negatives entirely and exposes the problem.
  • Optimising a metric you do not act on. If the deployed system applies a fixed threshold, tuning to ROC-AUC optimises a property the system never uses.
  • Metrics on a transformed target. RMSE on $\ln(y+1)$ is not RMSE in dollars — see Section 3.13.
  • MAPE with near-zero actuals. Mathematically undefined at zero and explosive near it.
  • Comparing $R^2$ across datasets. The denominator is dataset-specific, so a higher $R^2$ on a different dataset does not mean a better model.

Connecting the Metric to the Tuning Loop

Whatever you choose has to become the objective the search minimises:

# Hyperopt minimises, so a metric to maximise is negated
def objective(params):
    model = fit(params)
    f2 = fbeta_score(y_val, model.predict(X_val), beta=2.0)   # recall-weighted
    return {"loss": -f2, "status": STATUS_OK}
# Spark ML: the Evaluator passed to CrossValidator IS the selection criterion
evaluator = BinaryClassificationEvaluator(labelCol="label",
                                          rawPredictionCol="rawPrediction",
                                          metricName="areaUnderPR")

A frequent real-world failure — and a plausible exam distractor — is selecting the best model by one metric while reporting another. The evaluator handed to CrossValidator is what decides bestModel, so it must be the metric the business actually cares about.

One Metric to Optimise, Several to Watch

Tuning requires a single scalar, but reporting should not be reduced to one number. A workable convention is to nominate one optimisation metric and a set of guardrail metrics that must stay within agreed bounds:

RoleExample on a fraud modelBehaviour
Optimisation metricPR-AUCMaximised by the search
GuardrailFalse positives per 10,000 transactionsMust stay under the operations team's review capacity
Guardrailp95 inference latencyMust stay under the payment authorisation budget
GuardrailRecall on the highest-value segmentMust not regress against the incumbent

A candidate that wins on the optimisation metric but breaches a guardrail is rejected. This is exactly the shape of the automated validation gate described in Section 1.1, and it is why metric choice is an MLOps decision as much as a statistical one.

Translating a stated cost into $\beta$

$F_\beta$ treats recall as $\beta$ times as important as precision, so the direction of the cost asymmetry picks $\beta$ directly:

Stated cost relationshipChoose
False negatives are much more expensive$\beta > 1$ — typically $F_2$
Costs are roughly symmetric$\beta = 1$ — the ordinary $F_1$
False positives are much more expensive$\beta < 1$ — typically $F_{0.5}$

The exam does not ask for a numeric $\beta$; it asks you to read the asymmetry in the scenario and pick the metric that punishes the expensive error.

Test Your Knowledge

A hospital deploys a screening model for a serious disease. Missing a case can be fatal; a false alarm results in one additional low-cost confirmatory test. Which metric should the tuning loop optimise?

A
B
C
D
Test Your Knowledge

A fraud model operates at 0.2% positive prevalence. Which pair of choices is appropriate for comparing candidate models and for reporting performance at the deployed threshold?

A
B
C
D
Test Your Knowledge

A model's scores feed a downstream expected-loss calculation that multiplies the predicted probability by a dollar exposure. Which metric best reflects what this system needs from the model?

A
B
C
D