Skip to content

Main content

Metrics: Ranked Gain Tie Average Term Tool

Compute expected DCG contribution of one tied rank block by averaging supplied nonnegative gains across its explicit rank positions; no whole ranking metric.

Loading tool…

Description

Multiply their mean by the sum of 1/log2(rank + 1) over the consecutive tie-block ranks.

Ranking metrics compare order or discount relevance by position. Ties, one-based ranks, and normalization choices change the contribution of an individual pair or rank.

Multiply their mean by the sum of 1/log2(rank + 1) over the consecutive tie-block ranks.

When to use this tool

Use Metrics: Ranked Gain Tie Average Term when you need one rank discount, tie block, or pairwise contribution.

How to use the tool and how it works

  1. Enter gains, firstRank. Use the units and conventions below.
  2. Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
  3. Read result. Expand result to inspect the returned fields.

Require nonempty nonnegative gains and positive firstRank. Multiply their mean by the sum of 1/log2(rank + 1) over the consecutive tie-block ranks.1

Input fieldMeaning and unitsAccepted input
gainsGainsRequired. Array of finite number. Implementation limit: 128 items.
firstRankFirst RankRequired. Safe integer.
Output fieldInterpretationReturned shape
resultResultRequired. Object.
result.meanGainMean GainCalculated result member: number.
result.discountedTieBlockGainDiscounted Tie Block GainCalculated result member: number.
json
{
  "input": {
    "gains": [
      1,
      3
    ],
    "firstRank": 1
  },
  "output": {
    "result": {
      "meanGain": 2,
      "discountedTieBlockGain": 3.261859507142915
    }
  }
}

Limitations and assumptions

  • This averages supplied gains within a tie block; it does not transform relevance labels or normalize by an ideal ranking.
  • Outputs are nested inside result. Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
  • Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.

Alternative or Complementary methods

Evaluate the full ranked set with a documented gain transformation, tie convention, and normalization.

References

  1. Calculation and input contract: metrics/ranked-gain-tie-average-term — tool.io

Similar or alternative tools