Comparative performance analysis of three machine learning algorithms applied to sensor data in dairy cattle to predict metritis events I. Behaviors measured with an ear-tag accelerometer.

Dairy cattle behavioral data measured by an ear-tag accelerometer during the first 21 days postpartum was used to build predictive models for metritis events. Three machine learning classifiers were used to compare performance in terms of F1 score, using a rank-based method due to the unbalanced nature of the dataset. Performance for each combination of classifier, sensor data aggregation, and time before the event are reported at different cut-offs based on class probabilities.