Abstract
The decline in fed cattle cash sales and its impact on price discovery are concerning. This study extends existing literature by utilizing machine learning to explore factors, particularly decision trees and random forests, to explore factors influencing fed cattle price ranges, complementing traditional regression analyses. These models uncover hidden patterns and provide additional insights into the cattle market. Key variables such as weight range, head count, and trade location, are found to be associated with price ranges. Notably, the weight range emerges as the primary variable influencing the price range, with smaller weight ranges linked to lower price ranges.