Título: Application of Machine Learning for Hot Carcass Yield Prediction in Beef Cattle
Autores: Angelo Polizel Neto, Elton Fernandes dos Santos, João Pedro Lanzarini Lopes, Marçal Henrique Moreira, Julio Cesar Machado Alvares, Cecylyana Leite Cavalcante, Evelyn Prestes Brito, Guilherme Roberto Matos Silva, Emerson Amaral Santos, Priscila Dias da Silva & Rafael Sarto Zaratin
Resumo: Hot Carcass Yield (HCY) is a critical indicator of both productive efficiency and economic value in the meat processing industry. This study presents the development and evaluation o f predictive models based on Machine Learning (ML) techniques to accurately predict HCY using supervised learning algorithms trained on comprehensive historical slaughterhouse data. The dataset includes key variables such as breed, sex, age, and fat cover, which enabled the models to capture complex non -linear relationships influencing yield outcomes. Multiple ML algorithms were rigorously assessed through cross -validation to determine their predictive performance. The results reveal that the develope d models achieve high accuracy and robustness, demonstrating their practical applicability for improving monitoring, management, and decision -making in industrial and zootechnical processes. This research underscores the transformative potential of Machine Learning in precision livestock farming, advancing quality control, traceability, and data-driven optimization in the meat industry.
Palavras-chave: Computational Intelligence; Supervised Learning Models; Productive Efficiency.
Páginas: 8
Código DOI: 10.21528/CBIC2025-1191795
Artigo em PDF: CBIC_2025_paper1191795.pdf
Arquivo BibTeX:
CBIC_2025_1191795.bib