Investigation of factors affecting egg breakage resistance in laying hens using data mining and machine learning methods.

Random Forest accurately predicts eggshell breaking resistance in laying hens with an R2 of 0.852, outperforming other models and revealing key influencing factors.

• Why it matters: Understanding eggshell strength is vital for reducing egg breakage, which impacts economic losses and food safety; current predictive methods lack precision and insight into key traits.
• What they did: Researchers applied three machine learning algorithms—C5.0 decision tree, Random Forest, and Support Vector Regression—to predict eggshell strength based on traits like egg weight, shell weight, shell thickness, and shape index, using data from 464 eggs.
• The result: The Random Forest model not only achieved high predictive accuracy but also identified important traits affecting eggshell resistance, demonstrating the value of ensemble methods for improving egg quality management.