Interpretable machine learning for yak milk feeding pattern discrimination: Integrating XGBoost with multidimensional explainability analysis

TL;DR

This paper introduces a low-cost, interpretable machine learning method using XGBoost to distinguish yak milk feeding patterns based on routine compositional data.

Contribution

The novel contribution is integrating XGBoost with multidimensional explainability techniques for yak milk feeding pattern discrimination.

Findings

XGBoost achieved 92% accuracy and 0.94 AUC in classifying yak milk feeding patterns.

Fat content and lactose were identified as the most important discriminators using SHAP, PDP, and ICE analyses.

Interactions between fat, lactose, and freezing point were found to be biologically meaningful.

Abstract

Accurately identifying grazing (GZ) and supplementary feeding (SF) patterns in yak milk is important for product authentication; however, current methodologies are often expensive and time consuming. In this study, we examined 523 milk samples of lactating yaks at four stages of SF and tested 21 machine learning algorithms to develop a rapid and cost-effective classification method using routine compositional parameters. Ensemble learning techniques performed better than others, with XGBoost having the best accuracy (92%) and AUC (0.94). Multidimensional interpretability analyses, including SHAP, PDP, and ICE, identified fat content (27.8%) and lactose (23.1%) as the most important discriminators, along with biologically meaningful interactions, such as between fat, lactose, and freezing point. This interpretable framework provides a practical, low-cost method for milk authentication of yaks using ordinary dairy analyzers, providing a methodological foundation for the establishment of standardized GZ certification systems in milk production from yaks.

Unlabelled Image

•XGBoost achieved 92% accuracy for high-precision yak milk feeding pattern detection.•SHAP, PDP, and ICE methods explained XGBoost model decision mechanisms.•Routine milk composition data enables cost-effective feeding pattern classification.•SHAP revealed fat-freezing point and lactose-freezing point interaction effects.

XGBoost achieved 92% accuracy for high-precision yak milk feeding pattern detection.

SHAP, PDP, and ICE methods explained XGBoost model decision mechanisms.

Routine milk composition data enables cost-effective feeding pattern classification.

SHAP revealed fat-freezing point and lactose-freezing point interaction effects.

Figures