Application of the XGBoost Algorithm for Predicting the Target Effective Temperature in Closed Broiler Chicken Cage

Department of Mathematics, Sanata Dharma University, Yogyakarta, Indonesia

^* Corresponding author: yghartono@usd.ac.id

Abstract

Broiler chickens are a breed known for their rapid growth, typically reaching maturity in just 4-5 weeks. This growth is influenced by various factors, with cage management playing a significant role. One key factor in cage management is maintaining an optimal target temperature, which is determined by combining measurements of ambient temperature, humidity, and wind speed. This article examines how the XGBoost algorithm can be used to predict the target effective temperature in closed-house broiler chicken systems. The goal is to develop a predictive network model with high accuracy, enabling the regulation of cage conditions to ensure the chickens’ comfort. The study findings demonstrate that the proposed algorithm effectively models target temperatures, aiding in the management of cage conditions.