Back to search

University of Minnesota

Evaluation of an Early Reproductive Success Machine Learning Prediction for Multiparous Dairy Cows

Abstract

dc:description.abstract

Reproductive performance impacts the profitability of a dairy herd. The ability to understand the reproductive capabilities of individual cows and the use of targeted reproductive management could optimize reproductive performance of dairy herds. To address this need, the Early Reproductive Success prediction was developed using a Light Gradient-Boosting Machine Learning Algorithm, which included herd level reproduction data, weather data, genomic-enhanced PTA, individual cow information, milk production, health events, and previous lactation performance data. Two studies were conducted to evaluate the ability of the Early Reproductive Success algorithm to predict pregnancy probability by 110 DIM at 40-43 DIM, which was prior to the end of the voluntary waiting period for enrolled herds. The first study was a retrospective study that included 19,433 multiparous cows that calved in 2022 from seven US commercial herds. The best 10% Early Reproductive Success prediction deciles had better performance for proportion pregnant at 110 DIM, proportion of cows that gave birth to a live calf to initiate the following lactation, 18-month cow cash flow, 18-month slot cash flow, and 18-month ECM. The second study was a prospective, random controlled study. The study included 1,631 Holstein multiparous cows that calved from February 2024 through December 2024 at a single, commercial herd. Cows were randomly allocated to one of two treatment groups: laborious reproductive program (first breeding with Double Ovsynch) or simplified reproductive program (first breeding with Presynch-Ovsynch). Cows with higher Early Reproductive Success predictions had a higher proportion pregnant at 110 DIM; however, there was not a difference in proportion pregnant at 110 DIM between reproductive program treatments. These results demonstrated the ability of the Early Reproductive Success algorithm to predict differences in reproductive performance. Further research is needed to determine whether the Early Reproductive Success prediction has potential to be used to help dairy producers develop targeted reproductive management strategies.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Fessenden, Brenda

Subjects

dc:subject × 5

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Citation
Fessenden, Brenda. (2026). Evaluation of an Early Reproductive Success Machine Learning Prediction for Multiparous Dairy Cows. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/283085.

Chain of custody

source
Harvested from
University of Minnesota
Base URL
conservancy.umn.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Fessenden, Brenda. Evaluation of an Early Reproductive Success Machine Learning Prediction for Multiparous Dairy Cows. 2026. https://hdl.handle.net/11299/283085