Normalized cumulative gain as an alternative evaluation measure for genomic selection models
Felix Heinrich, Thomas M Lange, Faisal Ramzan, Mehmet Gültas, Armin O Schmitt · 2025
Read Normalized cumulative gain as an alternative evaluation measure for genomic selection models by Felix Heinrich, Thomas M Lange, Faisal Ramzan, Mehmet Gültas, Armin O Schmitt (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12715923.txt.
Description
Felix Heinrich and co-authors propose a better score for breeding prediction models in a 2025 paper. Genomic selection ranks animals and plants for breeding by DNA. Standard scores reward overall fit, not picking the best few.
A model can fit well yet choose mediocre parents for the next round. Normalized cumulative gain measures the payoff of the chosen top group. Four datasets from animals and plants tested the idea broadly. Nine common prediction methods were compared under both scoring styles. Rankings of methods shifted when selection gain was the target. Readers learn to judge breeding models by what breeding actually needs.
Catalog record
| CREATOR | Felix Heinrich, Thomas M Lange, Faisal Ramzan, Mehmet Gültas, Armin O Schmitt |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |