GOLD STANDARD

Scoring Methodology

How the GOLD Score Works

The GOLD Score is a quality benchmark score ranging from -50 to +50 that evaluates soybean meal against a market reference distribution. A score of 0 means the lot is at the benchmark median; positive scores indicate above-benchmark quality, and negative scores indicate below-benchmark quality.

The GOLD Score (v2A.1) uses a quantile-based benchmark method across 5 scored factor groups. For protein, sugars, and amino acids, each metric is positioned within the benchmark distribution using quantile interpolation. Protein uses diminishing returns above the median to avoid over-rewarding CP. Sugars uses an asymmetric curve that penalizes low values more heavily. KOH solubility uses a practical optimum range curve. TIA uses a plateau with staged penalty. The system is designed around two core principles: simplicity — a single number that captures multi-dimensional quality — and transparency — every weight, threshold, and formula is documented and inspectable.

Example: A lot scoring 12.4 falls in the Silver zone, above the benchmark average

12.4BronzeSilverGold-50050

The Problem: “Meets Spec but Performs Differently”

Two soybean meal lots can both pass purchase specifications yet deliver meaningfully different nutritional outcomes. Traditional pass/fail specifications don't capture the quality gradient within “acceptable” ranges. The GOLD Score addresses this gap by measuring how much a lot deviates from the Reference Population benchmark — turning a binary pass/fail into a continuous quality signal.

Inspired by Proven Relative Models

The GOLD Score follows the same relative evaluation paradigm used in two well-established domains:

Expected Progeny Differentials (EPDs)

In livestock breeding, animals are evaluated relative to their peers rather than on an absolute scale. An EPD of +5 means the animal is expected to produce offspring 5 units above the breed average. The GOLD Score applies this same concept to soybean meal quality.

Corn Suitability Ratings (CSRs)

In agricultural land evaluation, CSRs rate land relative to a reference standard rather than assigning an absolute productivity number. This relative approach makes comparisons meaningful across different contexts — the same principle behind the GOLD Score.

Quality Tiers

The final GOLD Score maps to one of three quality tiers, plus a safety reject gate for extreme TIA

+20
GoldScore ≥ +20

Significantly above benchmark — meets or exceeds all key reference population standards.

0
SilverScore 0 to +19

At or above benchmark — meets most reference population standards with minor gaps.

<0
BronzeScore < 0

Below benchmark — significant gaps vs. reference population identified.

RejectedScore TIA ≥ 6.0

Extreme TIA — lot flagged as Rejected regardless of raw score. Raw score is still computed for diagnostics.

Score Calculation (v2A.1)

GOLD v2A.1 benchmarks each lot against the market reference distribution and converts the result into a single score from -50 to +50.

1. Position within the benchmark distribution

For each amino acid, estimate where the lot sits within the benchmark distribution using the benchmark quantiles: q05, q25, q50, q75, q95

Then convert that percentile position into a utility score:

Utility = clip((percentile position − 0.05) / 0.90, 0, 1)

Crude Protein uses diminishing returns above the median: below q50, standard percentile-to-utility; above q50, utility flattens through anchors q50→0.50, q75→0.65, q95→0.80, capped at 0.80.

Sugars uses an asymmetric curve: zero utility at or below q25, rising to 0.45 at q50, 0.85 at q75, and 1.00 at q95. Low sugars are penalized more heavily than high sugars are rewarded.

A utility score of 0 means clearly weak versus benchmark

A utility score of 0.5 means roughly benchmark-average

A utility score of 1 means clearly strong versus benchmark

2. KOH practical optimum range

KOH is not treated as “higher is always better.” Instead, GOLD v2A.1 uses a practical optimal range informed by USSEC domain feedback:

0 utility at 70 or below

Utility rises linearly from 70 to 78

Full utility from 78 to 85

Utility falls linearly from 85 to 88

0 utility at 88 or above

This captures both under-processing and over-processing. The wider plateau (78–85) reflects domain consensus that the practical optimum extends higher than originally modeled.

3. TIA plateau + staged penalty + reject gate

TIA is not rewarded indefinitely for becoming lower and lower. GOLD v2A.1 uses a plateau with staged penalty and a hard reject gate:

Full utility from 2.0 to 3.0 mg/g (practical optimum)

No extra reward for TIA below 2.0 — utility stays at 1.0

Decline to 0.50 at 4.0

Steeper decline to 0 at 5.5

TIA ≥ 6.0 mg/g REJECTED regardless of other metrics

Beyond the utility curve, a composite-level haircut of MAX(0, (TIA − 3.5) × 0.04) is subtracted from the weighted composite before scaling. Additionally, when TIA is below 1.5 mg/g and KOH is below 75%, a 0.10 utility penalty is applied to the TIA pillar — this combination may signal over-processing where excessive heat has deactivated TIA but also damaged protein solubility.

4. Amino acid block

Each amino acid is scored separately, then combined into one amino acid utility:

AA Utility = 0.5 × average(amino acid utilities) + 0.5 × minimum(amino acid utility)

This rewards overall balance while still penalizing the weakest amino acid.

5. Center each component and build the weighted composite

Convert each utility score to a centered score:

Centered score = 2 × utility − 1

−1 = weak

0 = benchmark-neutral

+1 = strong

Then calculate the raw composite:

Raw Composite = 0.30 × CP + 0.27 × KOH + 0.20 × Amino Acids + 0.17 × Sugars + 0.06 × TIA

In this formula, each term refers to the centered score for that component.

6. TIA composite haircut + final GOLD Score

Before scaling, a composite-level haircut is applied for elevated TIA:

Adjusted Composite = Raw Composite − MAX(0, (TIA − 3.5) × 0.04)

Then convert to the final bounded score:

GOLD Score = clip(50 × Adjusted Composite, −50, +50)

If TIA ≥ 6.0 mg/g, the displayed status is Rejected regardless of the raw score. The raw score is still computed for diagnostic purposes.

How to read the score

0 = benchmark middle

positive = above benchmark

negative = below benchmark

−50below benchmark|0|above benchmark+50

Weight Hierarchy

Contribution of each metric to the final score (must sum to 100)

Metric Scoring Details

Crude Protein (CP)
30%
Higher is better (diminishing returns above median)

Primary indicator of nutritional value. Below the benchmark median, higher protein earns proportional credit. Above the median, returns diminish — utility is capped at 0.80 above q95. This avoids over-rewarding CP since amino acids have their own pillar.

KOH Solubility
27%
Optimal range: 78–85%

Measures protein digestibility after processing. Scored with a practical optimum curve: full utility at 78–85%, linearly decreasing outside this range. Below 70% or above 88% receives zero utility.

Essential Amino Acids
20%
Higher is better (mean/min blend)

Composite score of 5 essential amino acids (LYS, MET, CYS, THR, TRP). Each AA is scored against the benchmark distribution, then combined as 50% average + 50% minimum. This rewards overall balance while penalizing the weakest amino acid.

Sugars
17%
Higher is better (asymmetric utility)

Energy proxy contributing to metabolizable energy in the feed ration. Low sugars (≤q25) receive zero utility — a meaningful penalty. Above the median, sugars earn strong credit up to full utility at q95.

Trypsin Inhibitor (TIA)
6%
Lower is better (plateau + staged penalty)

Anti-nutritional factor that inhibits protein digestion. Full utility at TIA 2.0–3.0 mg/g (practical optimum). Decline to 0.50 at 4.0, steeper decline to 0 at 5.5. TIA ≥ 6.0 mg/g results in automatic rejection regardless of other metrics. A 0.10 utility penalty is applied when TIA is below 1.5 and KOH is below 75% (under-processing signal).

Trypsin Inhibitor Correlation Analysis

Two key relationships illustrate how Trypsin Inhibitor (TI) levels relate to other processing quality indicators. Data digitized from published research on SBM quality assessment.

TI vs Urease Activity (UA)

414 SBM samples from 19 countries. Higher TI tends to correlate with higher urease activity, both indicating under-processing.

Y: Urease Activity (pH units)

TI vs KOH Protein Solubility

70 SBM samples from Brazil. Lower TI generally corresponds to higher KOH solubility, indicating well-processed meal with good protein digestibility.

Y: KOH Protein Solubility (%)

Both charts confirm that Trypsin Inhibitor is a reliable marker of processing quality. In the UA chart, samples with TI above ~4 mg/g show elevated urease activity, signaling under-processing. In the KOH chart, lower TI values cluster with higher protein solubility (75–86%), indicating effective heat treatment that preserves digestibility while deactivating anti-nutritional factors.