A Neural network model for the prediction of cattle prices in South African livestock actions

Résumé

Abstract – This study developed a neural network model for predicting cattle prices in South African livestock auctions based on breed (B), weight (W), time/season (T) and price (P) variables. Using the online auction dataset from 2023 - 2025, the model analyzed nonlinear relationships influencing price fluctuations, producing realistic per-cattle predictions ranging between ZAR 7,000 - ZAR 17,500, with projected increases up to ZAR 22,000 in future weeks. The results demonstrate the model’s capacity to capture market dynamics shaped by breed attributes, seasonal demand fluctuations, and animal mass. The results illustrate that artificial intelligence-led techniques, including neural networks, can substantially improve market prediction accuracy, enhance profitability, and inform strategic decisions in the livestock sector. Furthermore, this study provides a foundation for future research to expand predictive modelling beyond cattle, contributing to the development of a comprehensive livestock price prediction system that integrates multiple animal types under a unified intelligent forecasting framework.

Citer ce document

Accès au document

Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter

Voir l'article sur le site de la revue

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0