<![CDATA[The global cattle sector is essential for food provision, livelihood support, economic benefits, land restoration, and energy generation. Precise assessment of cow weight is crucial for farmers to track animal growth, while for traders, ascertaining the exact weight of cattle is imperative for establishing the price of the meat they acquire. This paper introduces an innovative method for predicting cattle weight via the random forest regression technique. This study employs a dataset consisting of thirteen variables: live weight, age, withers height, sacrum height, chest depth, chest width, clock width, hip joint width, slant body length, slant back length, chest circumference, metacarpal thickness, and half of the dorsal surface thickness. The findings indicate that the random forest regression technique produced the most precise predictions of cattle weight, with a mean absolute error (MAE) of 21.902 kg, a mean absolute percentage error (MAPE) of 4.201%, a root mean square error (RMSE) of 29.433 kg, and an R² value of 0.761. The findings underscore the model's efficacy in accurately predicting cattle weight, offering significant insights for agricultural management and commercial trading sectors.]]>
Copyrights © 2025
