![[SRC-140] Rapid methods and classification (PDF sheet 14)](https://images.spr.so/cdn-cgi/imagedelivery/j42No7y-dcokJuNgXeA0ig/f9faaa5a-12e7-445b-ab82-4c95c0f0f700/attachment-4c9836e8-5dbd-420f-8f7b-ee710b211b04-us_whiskey_academy/w=1920,quality=90,fit=scale-down)
![[SRC-140] Rapid methods and classification (PDF sheet 14)](https://images.spr.so/cdn-cgi/imagedelivery/j42No7y-dcokJuNgXeA0ig/95dc2f1d-5993-42f1-a7c0-c08fe42504f7/whiskey_research/w=1920,quality=90,fit=scale-down)
The percentages apply to this selected dataset and do not establish universal category authentication performance.
The conclusion states the scope and reported classification results.
Repeated splits of 16 products into 13 training and three test products produced high classification results. The headline 97.86% sensory result is the share of repetitions with all three test products correct, not standard per-product accuracy; reported mean test accuracy was 99.03%. Chemical PCA results differ between 96.98% in results and 96.94% in the conclusion.
14
PDF sheet 7
Rapid methods and classification
Rechecked 2026-09-27 sheets 7–8 and 12–14. Replaced ambiguous in-sample wording: held-out products were tested, but repeatedly within the same small selected dataset. No independent external validation.
Capture evidence faithfully. Select one Source, record a usable locator, and preserve enough surrounding context to prevent misquotation.
Evidence
Paste the exact quote, paraphrase, statistic, definition, or source claim into Excerpt Text. Use Excerpt Type to distinguish quotation from interpretation.
Location and context
Record Locator Type, Locator Start, Locator End when needed, and Source Section. Explain the surrounding argument in Context.
Annotation
In Annotation, state why this evidence matters. Add approved Tags for retrieval and connect it to every relevant Literature Note.