Evaluating Predictive Models for Predicting Total Score of Beef Carcasses

Author

Emmanuel Forson, Stephen F Austin State UniversityFollow

Date of Award

Spring 5-8-2025

Degree Type

Thesis

Degree Name

Master of Science - Mathematical Sciences

Department

Mathematics and Statistics

First Advisor

Dr. Jacob Pratsher

Second Advisor

Dr. Jacob Turner

Third Advisor

Dr. Kent Riggs

Fourth Advisor

Dr. Douglas Smith

Abstract

The beef industry plays a vital role in global agriculture, with carcass quality and consumer preference being key determinants of market success. This thesis examines predictive modeling techniques for estimating the Total Score of beef carcasses, a composite measure representing yield and quality, primarily used by the Nebraska Cattlemen Association. Using data from the Nebraska Cattlemen’s Foundation Retail Value Steer Challenge (2000–2023), the study compares the performance of First Order Multiple Linear Regression (MLR) with three machine learning techniques: K-Nearest Neighbors (KNN), Random Forest, and Gradient Boosting Machine (GBM).

The analysis focuses on six key predictors: Hot Carcass Weight, Back Fat Thickness, Ribeye Area, Final Yield Grade, Final Carcass Retail Value, and Year. Two modeling scenarios are evaluated: (1) training on a large dataset (2000–2021) and validating on recent years (2022–2023), and (2) smaller rolling window subsets (five-year training to predict the next two years, iterated across the full dataset). Performance is assessed using metrics such as Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and Accuracy Percentage.

Results show that while MLR provides interpretable models, modern machine learning models offer higher predictive accuracy in scenarios with limited and complex data, effectively capturing non-linear relationships and interactions. This research extends previous works that relied solely on MLR by integrating modern machine learning techniques into beef carcass prediction, offering practical recommendations for stakeholders and setting a benchmark for data-driven evaluation methods that can support improved decision-making in beef production.

Repository Citation

Forson, Emmanuel, "Evaluating Predictive Models for Predicting Total Score of Beef Carcasses" (2025). Electronic Theses and Dissertations. 601.
https://scholarworks.sfasu.edu/etds/601

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.