A cutting-edge framework for surface roughness prediction using multiverse optimization-driven machine learning algorithms

In this technical paper, we present a comprehensive study on the performance of the Multiverse Optimization (MVO) algorithm combined with various machine learning models, including Decision Trees, Artificial Neural Networks, Random Forest, and XGBoost. Our primary goal is to investigate the efficacy of the MVO algorithm in enhancing the performance of these models when applied to a specific dataset and problem context. Performance metrics, such as mean squared error (MSE), mean absolute error (MAE), and R-squared value, are employed to evaluate and compare the effectiveness of each MVO-enhanced model. Our results demonstrate that the MVO-Decision Tree combination outperforms the other MVO-enhanced models, exhibiting lower MSE and MAE values and a higher R-squared value. We attribute this superior performance to several factors, including problem suitability, the metaheuristic optimization capabilities of the MVO algorithm, the simplicity and interpretability of Decision Trees, and effective model selection and hyperparameter tuning.