āĻŽā§ŒāϞāĻŋāĻ• āύāĻŋāĻ°ā§āĻĻ⧇āĻļāĻŋāĻ•āĻž

F1 Score and F-Beta

F1 combines precision and recall through their harmonic mean, rewarding a classifier only when both are reasonably strong.

āĻāχ āύāĻŋāĻ°ā§āĻĻ⧇āĻļāĻŋāĻ•āĻž āĻļ⧁āύ⧁āύāĻāφāχ-āĻŦāĻ°ā§āĻŖāĻŋāϤ ¡ ~3 min

āĻāχ āĻĒ⧃āĻˇā§āĻ āĻžāϝāĻŧ3 āĻŽāĻŋāύāĻŋāϟ āĻĒāĻĄāĻŧāĻž āĻšāϝāĻŧ⧇āϛ⧇
  1. āĻ“āĻ­āĻžāϰāĻ­āĻŋāω
  2. āĻ—āĻ­ā§€āϰ āĻĄā§āĻŦ
  3. āĻŦāĻžāĻ¸ā§āϤāĻŦ-āĻŦāĻŋāĻļā§āĻŦ āĻŦāĻžāĻ¸ā§āϤāĻŦāĻžāϝāĻŧāύ
  4. The Future of F1 Score and F-Beta
  5. āĻāϟāĻžāϕ⧇ āĻŦāĻžāĻ¸ā§āϤāĻŦ⧇ āĻĒā§āϰāϝāĻŧā§‹āĻ— āĻ•āϰāĻž āĻšāĻšā§āϛ⧇
  6. āĻ…āĻ¨ā§āĻŦ⧇āώāĻŖ āϚāĻžāϞāĻŋāϝāĻŧ⧇ āϝāĻžāύ
  7. āĻĒā§āϰāĻžāϝāĻŧāĻļāχ āϜāĻŋāĻœā§āĻžāĻžāϏāĻŋāϤ āĻĒā§āϰāĻļā§āύāĻžāĻŦāϞ⧀

āĻ“āĻ­āĻžāϰāĻ­āĻŋāω

F-beta uses a parameter to put more weight on recall or precision for a stated task. These scores depend on the chosen positive class, threshold and averaging method and do not summarize every cost or fairness concern.

āĻ—āĻ­ā§€āϰ āĻĄā§āĻŦ

Precision asks what share of predicted positive cases are truly positive; recall asks what share of actual positive cases were found. F1 combines them as the harmonic mean, 2 × precision × recall divided by their sum when that denominator is nonzero. The harmonic mean falls when one component is low, so a classifier cannot earn a high F1 merely by excelling at one side. The score is useful for comparing systems with the same task definition, but it does not tell a team which kind of mistake matters more. Consider invented counts of eight true positives, two false positives and eight false negatives. Precision is 8/(8+2) = 0.8 and recall is 8/(8+8) = 0.5. F1 is 2 × 0.8 × 0.5/(0.8+0.5), about 0.615. The equivalent count formula is 2TP/(2TP+FP+FN), or 16/26. Report the counts as well as the score so readers understand what happened. F-beta generalizes F1. When beta is greater than one, recall carries more weight; when beta is less than one, precision does. F2 may suit a screening workflow where missing a relevant case is more costly than sending another case for review, but the choice needs an operational justification. It does not eliminate the need to inspect false positives, capacity limits or subgroup outcomes. A threshold change can trade precision against recall and therefore alter F-beta even if the underlying score model is unchanged. For multiple classes, macro averaging computes the per-class result and then gives each class equal weight. Micro averaging pools true positives, false positives and false negatives across classes before computing the score. These answer different questions when class frequencies vary. State the positive label and averaging rule explicitly. An F1 number says nothing directly about probability calibration, economic cost, or whether a small subgroup is being missed. Evaluate those separately, and use a held-out dataset that represents the decisions the model will face.

āĻŦāĻžāĻ¸ā§āϤāĻŦ-āĻŦāĻŋāĻļā§āĻŦ āĻŦāĻžāĻ¸ā§āϤāĻŦāĻžāϝāĻŧāύ

A screening team reports F2 when missing relevant cases is costlier than reviewing an extra false alert, while still showing both precision and recall.

An analyst computes F1 from eight true positives, two false positives and eight false negatives in a constructed example.

A multiclass evaluator reports macro F1 to show how uncommon classes perform instead of presenting only an overall average.

A product team compares metrics at several decision thresholds and verifies that the chosen setting fits review capacity and error costs.

The Future of F1 Score and F-Beta

As AI evaluations cover more classes and deployment settings, a single F1 number will become less adequate for decision making. Teams may use F-beta to encode a documented preference for recall or precision, but a beta value is still a simplification of real costs. Better reports should show the counts, averaging rule, operating threshold and uncertainty together. Changing populations can alter precision even if recall stays stable, so metrics need refresh after deployment. Future dashboards may make tradeoffs easier to explore, but the choice of who bears each error remains a policy and product decision that no formula can settle automatically.

āĻāϟāĻžāϕ⧇ āĻŦāĻžāĻ¸ā§āϤāĻŦ⧇ āĻĒā§āϰāϝāĻŧā§‹āĻ— āĻ•āϰāĻž āĻšāĻšā§āϛ⧇

āϕ⧇āύ āĻāϟāĻž āϗ⧁āϰ⧁āĻ¤ā§āĻŦāĻĒā§‚āĻ°ā§āĻŖ

  • āϏ⧁āĻ¸ā§āĻĒāĻˇā§āϟ āϏāĻŋāĻĻā§āϧāĻžāĻ¨ā§āϤ. āĻāϟāĻŋ āφāĻĒāύāĻžāϕ⧇ āĻŦāĻŋāĻĒāĻŖāύ⧇āϰ āĻ­āĻžāώāĻž āĻĨ⧇āϕ⧇ āĻ¸ā§āĻĒāĻˇā§āϟ āĻĒā§āϰāϝ⧁āĻ•ā§āϤāĻŋāĻ—āϤ āĻĻāĻžāĻŦāĻŋāϗ⧁āϞāĻŋ āφāϞāĻžāĻĻāĻž āĻ•āϰāϤ⧇ āϏāĻšāĻžāϝāĻŧāϤāĻž āĻ•āϰ⧇āĨ¤
  • āĻ–āϰāϚ āĻ“ āĻŦāĻžāĻœā§‡āϟ. āĻ…āĻ°ā§āĻĨ āĻŦāĻž āϏāĻŽāϝāĻŧ āĻŦā§āϝāϝāĻŧ āĻ•āϰāĻžāϰ āφāϗ⧇ āφāĻĒāύāĻŋ āφāϰāĻ“ āĻ­āĻžāϞ āĻŦāĻžāĻ¸ā§āϤāĻŦāĻžāϝāĻŧāύ āĻĒā§āϰāĻļā§āύ āϜāĻŋāĻœā§āĻžāĻžāϏāĻž āĻ•āϰāϤ⧇ āĻĒāĻžāϰ⧇āύāĨ¤
  • āϟāĻŋāĻŽ āĻāĻŦāĻ‚ āĻ“āϝāĻŧāĻžāĻ°ā§āĻ•āĻĢā§āϞ⧋. āĻ­āĻžāĻ— āĻ•āϰāĻž āĻŦā§‹āĻāĻžāĻĒāĻĄāĻŧāĻž āϏāĻš āĻĻāϞāϗ⧁āϞāĻŋ āφāϰāĻ“ āĻ­āĻžāϞ āĻĒāĻŖā§āϝ, āύ⧀āϤāĻŋ āĻāĻŦāĻ‚ āĻļ⧇āĻ–āĻžāϰ āϏāĻŋāĻĻā§āϧāĻžāĻ¨ā§āϤ āύ⧇āϝāĻŧāĨ¤

āϜāĻ¨ā§āϝ āϏāϤāĻ°ā§āĻ•

  • āĻŦāĻŋāĻ­āĻŋāĻ¨ā§āύ āĻĻāϞ āĻāĻ•āχ āĻļāĻŦā§āĻĻāϟāĻŋ āĻ­āĻŋāĻ¨ā§āύāĻ­āĻžāĻŦ⧇ āĻŦā§āϝāĻŦāĻšāĻžāϰ āĻ•āϰāϤ⧇ āĻĒāĻžāϰ⧇, āϤāĻžāχ āϏ⧁āϝ⧋āĻ—āϟāĻŋ āφāϗ⧇ āĻĨ⧇āϕ⧇āχ āύāĻŋāĻ°ā§āϧāĻžāϰāĻŖ āĻ•āϰ⧁āύāĨ¤
  • āĻŦ⧇āĻžā§āϚāĻŽāĻžāĻ°ā§āĻ•āϗ⧁āϞāĻŋ āĻļāĻ•ā§āϤāĻŋāĻļāĻžāϞ⧀ āĻĻ⧇āĻ–āĻžāϤ⧇ āĻĒāĻžāϰ⧇ āϝāĻ–āύ āĻŦāĻžāĻ¸ā§āϤāĻŦ-āĻŦāĻŋāĻļā§āĻŦ⧇āϰ āĻ•āĻ°ā§āĻŽāĻ•ā§āώāĻŽāϤāĻž āĻ…āϏāĻŽ āĻšāϝāĻŧāĨ¤
  • āĻĄā§‡āϟāĻž āϗ⧁āĻŖāĻŽāĻžāύ āĻāĻŦāĻ‚ āĻŽā§‚āĻ˛ā§āϝāĻžāϝāĻŧāύ āĻĒāϰāĻŋāĻ•āĻ˛ā§āĻĒāύāĻž āωāĻĒ⧇āĻ•ā§āώāĻž āĻ•āϰāĻž āĻĒā§āϰāĻžāϝāĻŧāχ āĻ­āĻ™ā§āϗ⧁āϰ āĻĢāϞāĻžāĻĢāϞ āϤ⧈āϰāĻŋ āĻ•āϰ⧇āĨ¤

āĻĒāϰāĻŦāĻ°ā§āϤ⧀ āĻĒāĻĻāĻ•ā§āώ⧇āĻĒ

  1. āφāĻĒāύāĻžāϰ āĻĒā§āϰāϝāĻŧā§‹āϜāύ⧀āϝāĻŧ āĻĢāϞāĻžāĻĢāϞ⧇āϰ āĻāĻ•āϟāĻŋ āϏāϰāϞ-āĻ­āĻžāώāĻž āϏāĻ‚āĻœā§āĻžāĻž āĻĻāĻŋāϝāĻŧ⧇ āĻļ⧁āϰ⧁ āĻ•āϰ⧁āύāĨ¤
  2. āĻĒāϰ⧀āĻ•ā§āώāĻžāϰ āφāϗ⧇ āĻāĻ•āϟāĻŋ āϏāĻžāĻĢāĻ˛ā§āϝ⧇āϰ āĻŽā§‡āĻŸā§āϰāĻŋāĻ• āĻāĻŦāĻ‚ āĻāĻ•āϟāĻŋ āĻŦā§āϝāĻ°ā§āĻĨāϤāĻžāϰ āĻļāĻ°ā§āϤ āĻŦāĻžāϛ⧁āύāĨ¤
  3. āĻāĻ•āϟāĻŋ āĻĒāĻžāϞāĻŋāĻļ āĻĄā§‡āĻŽā§‹ āϏ⧇āϟ āύāϝāĻŧ, āĻĒā§āϰāϤāĻŋāύāĻŋāϧāĻŋ āĻĄā§‡āϟāĻž āϏāĻš āĻāĻ•āϟāĻŋ āϛ⧋āϟ āĻĒāĻžāχāϞāϟ āϚāĻžāϞāĻžāύ⧎
  4. Document where F1 Score and F-Beta helps and where simpler methods are better.

āĻ…āĻ¨ā§āĻŦ⧇āώāĻŖ āϚāĻžāϞāĻŋāϝāĻŧ⧇ āϝāĻžāύ

āĻĢā§āϰāĻŋ āύāĻŋāωāϜāϞ⧇āϟāĻžāϰ

āĻĒā§āϰāϤāĻŋāĻĻāĻŋāύ⧇āϰ āĻāφāχ āĻŦā§āϰāĻŋāĻĢāĻŋāĻ‚ āĻĒāĻžāύ

āĻĒā§āϰāϤāĻŋ āϏāĻĒā§āϤāĻžāĻšā§‡āϰ āĻ•āĻžāĻœā§‡āϰ āĻĻāĻŋāύ āϏāĻ•āĻžāϞ⧇ āϤāĻŋāύāϟāĻŋ āϝāĻžāϚāĻžāχāĻ•ā§ƒāϤ āĻāφāχ āĻ¸ā§āĻŸā§‹āϰāĻŋ, āϏāĻšāϜ āχāĻ‚āϰ⧇āϜāĻŋāϤ⧇ āϞ⧇āĻ–āĻžāĨ¤ āϚāĻŋāϰāĻ•āĻžāϞ⧇āϰ āϜāĻ¨ā§āϝ āĻĢā§āϰāĻŋ, āϕ⧋āύ⧋ āĻŦāĻŋāĻœā§āĻžāĻžāĻĒāύ āύ⧇āχāĨ¤

āĻĒā§āϰāϤāĻŋ āϏāĻĒā§āϤāĻžāĻšā§‡āϰ āĻ•āĻžāĻœā§‡āϰ āĻĻāĻŋāύ⧇ āĻāĻ•āϟāĻŋ āχāĻŽā§‡āϞāĨ¤ āĻāĻ• āĻ•ā§āϞāĻŋāϕ⧇āχ āφāύāϏāĻžāĻŦāĻ¸ā§āĻ•ā§āϰāĻžāχāĻŦ āĻ•āϰ⧁āύāĨ¤ āφāĻŽāϰāĻž āĻ•āĻ–āύ⧋āχ āφāĻĒāύāĻžāϰ āĻ āĻŋāĻ•āĻžāύāĻž āĻŦāĻŋāĻ•ā§āϰāĻŋ āĻŦāĻž āĻļā§‡ā§ŸāĻžāϰ āĻ•āϰāĻŋ āύāĻžāĨ¤

āύāĻŋāĻœā§‡āϕ⧇ āĻĒāϰ⧀āĻ•ā§āώāĻž āĻ•āϰ⧁āύ

Take the F1 Score and F-Beta quiz

āĻĒā§āϰāϤāĻŋāϟāĻŋ āωāĻ¤ā§āϤāϰ⧇āϰ āϤāĻžā§ŽāĻ•ā§āώāĻŖāĻŋāĻ• āĻĢāĻŋāĻĄāĻŦā§āϝāĻžāĻ•, āĻāĻŦāĻ‚ āϕ⧋āĻ°ā§āϏ āĻĒāĻžāϏ āĻ•āϰāĻžāϰ āĻĒāϰ āϝāĻžāϚāĻžāχāϝ⧋āĻ—ā§āϝ āφāχāĻĄāĻŋ āϏāĻš āĻāĻ•āϟāĻŋ āĻļā§‡ā§ŸāĻžāϰāϝ⧋āĻ—ā§āϝ āϏāĻžāĻ°ā§āϟāĻŋāĻĢāĻŋāϕ⧇āϟāĨ¤

āϕ⧁āχāϜ āĻļ⧁āϰ⧁ āĻ•āϰ⧁āύ

āĻĢā§āϰāĻŋ āĻāφāχ āĻļāĻŋāĻ•ā§āώāĻžāϕ⧇ āϏāĻŽāĻ°ā§āĻĨāύ āĻ•āϰ⧁āύāĨ¤ AI Understanding āĻāĻ•āϟāĻŋ 501(c)(3) āĻ…āϞāĻžāĻ­āϜāύāĻ• āĻĒā§āϰāϤāĻŋāĻˇā§āĻ āĻžāύ — āϕ⧋āύ⧋ āĻŦāĻŋāĻœā§āĻžāĻžāĻĒāύ āύ⧇āχ, āϕ⧋āύ⧋ āĻĒ⧇āĻ“ā§ŸāĻžāϞ āύ⧇āχ, āĻ•āĻ–āύ⧋āχ āύāĻžāĨ¤ āĻāĻ•āϟāĻŋ āĻĻāĻžāύ āĻ•āϰ⧁āύ

āĻĒā§āϰāĻžāϝāĻŧāĻļāχ āϜāĻŋāĻœā§āĻžāĻžāϏāĻŋāϤ āĻĒā§āϰāĻļā§āύāĻžāĻŦāϞ⧀

What is F1 Score and F-Beta?

F1 combines precision and recall through their harmonic mean, rewarding a classifier only when both are reasonably strong. F-beta uses a parameter to put more weight on recall or precision for a stated task. These scores depend on the chosen positive class, threshold and averaging method and do not summarize every cost or fairness concern.

How does F1 combine precision and recall?

F1 is 2PR/(P+R), the harmonic mean of precision and recall when defined.

In the guide's constructed 8 TP, 2 FP and 8 FN example, what is F1 approximately?

The count formula gives F1 = 2TP/(2TP+FP+FN) = 16/26 ≈ 0.615.

When beta is greater than one in F-beta, which component receives more weight?

F-beta with beta greater than one emphasizes recall relative to precision, without removing precision.

A task values avoiding false alerts more than catching every positive case. Which beta direction can reflect that priority?

A beta between zero and one weights precision more heavily, though actual task costs still need review.

What does macro F1 do across multiple classes?

Macro averaging gives equal weight to each class's F1, making minority-class behavior more visible than a prevalence-weighted summary.

āĻļāĻŋāĻ–āϤ⧇ āĻĨāĻžāϕ⧁āύ

āϏāĻŽā§āĻĒāĻ°ā§āĻ•āĻŋāϤ āĻ—āĻžāχāĻĄ

āĻāχ āĻŦāĻŋāώāϝāĻŧ⧇āϰ āϜāĻ¨ā§āϝ āĻŦāĻžāĻ›āĻžāχ āĻ•āϰāĻž āφāϰāĻ“ āĻ—āĻžāχāĻĄ

āĻāĻ•āϟāĻŋ āĻŦāĻŋāύāĻžāĻŽā§‚āĻ˛ā§āϝ⧇ AI āĻļāĻ‚āϏāĻžāĻĒāĻ¤ā§āϰ āĻĒāĻžāύāĻāĻ•āϟāĻŋ āϏāĻ‚āĻ•ā§āώāĻŋāĻĒā§āϤ āĻŦāĻŋāύāĻžāĻŽā§‚āĻ˛ā§āϝ⧇ āϕ⧋āĻ°ā§āϏ āĻāĻŦāĻ‚ āĻĒāϰ⧀āĻ•ā§āώāĻž. āϕ⧋āύ⧋ āĻ–āϰāϚ āύ⧇āχ, āϕ⧋āύ⧋ āĻ•āĻžāĻ°ā§āĻĄ āύ⧇āχāĨ¤ āĻĒā§āϰāĻžāϝāĻŧ 2.5 āϘāĻ¨ā§āϟāĻžāĨ¤āĻŦāĻŋāύāĻžāĻŽā§‚āĻ˛ā§āϝ⧇ āĻļ⧁āϰ⧁ āĻ•āϰ⧁āύ →