Machine learning for ranking multivariate variables in cattle breeds raised in Paraguayan wetlands /Aprendizado de maquina para classificacao de variaveis multivariadas em racas bovinas criadas em pantanos do Paraguai

This study focuses on the performance of cows for meat production raised in the wetlands of Paraguay, examining five cattle genotypes: Brahman, Brangus, and Nelore, as well as two local breeds at risk of extinction. The main objective is to identify and rank phenotypic variables, including blood, clinical, hair, and health variables, demonstrating causal linkage with the live weight of the cows analyzed. Initially, high correlations were identified between different variables included in this study; then, using advanced Machine learning (ML) techniques and the application of Shapley additive explanations (SHAP), a deeper understanding was provided of the factors strongly associated with adaptability in these environments, and, therefore, the respective zootechnical performance. The association between cattle genotypic components linked with the season of the year proved to be the most influential factor on cattle live weight. Variables such as hair length, hematocrit, phosphatase, phosphorus, creatine phosphokinase, creatinine, protein, cortisol, calcium, and the presence of endoparasites were highlighted, demonstrating their hierarchical importance for animal selection. ML models are effective tools for establishing hierarchies ofrelevance in complex phenotypic multivariable, which is crucial in breeding programs for different zootechnical species and in special and specific environments like wetlands. Key words: cattle adaptability in wetlands, SHAP, phenotypic variables, blood variables Este estudo foca no desempenho de vacas para producao de carne, criadas nos pantanos do Paraguai, examinando cinco genotipos bovinos; Brahman, Brangus, Nelore, bem como duas racas locais em risco de extincao. O principal objetivo e identificar e classificar variaveis fenotipicas que incluem variaveis sanguineas, clinicas, de pelagem e saude, demonstrando ligacao causal com o peso vivo das vacas analisadas. Inicialmente, foram identificadas correlacoes elevadas entre diferentes variaveis incluidas neste estudo, e, entao, utilizando tecnicas avancadas de aprendizado de maquina e a aplicacao de explicacoes aditivas de Shapley (SHAP), foi proporcionado um entendimento mais profundo dos fatores fortemente associados a adaptabilidade nestes ambientes, e, portanto, o respectivo desempenho zootecnico. A associacao entre o componente genotipico bovino ligado a estacao do ano mostrou ser o fator influente mais predominante sobre o peso vivo bovino. Variaveis como comprimento do pe