To do this study's goal, parametric modeling, fnite-element analysis (FEA), and advanced optimization techniques will be used to rate the features of fxator products. The application of Grey Wolf Optimization (GWO) and XGBoost is employed to improve the accuracy of forecasts. A total of 89 distinct fxator product cases were analyzed in this study, utilizing SolidWorks CAD and ANSYS FEA software. Six geometric features were collected, and calculations on physical attributes were conducted. Exploratory data analysis (EDA) is a systematic approach used to thoroughly examine and develop a full grasp of a dataset before making any substantial fndings or generating assumptions. This study provides evidence that notable enhancements in model performance can be attained. This basic version of the XGBoost model does a great job of predicting the future. Its mean absolute error (MAE) is about 0.213, its mean squared error (MSE) is about 0.084, its root-mean squared error (RMSE) is about 0.290, and its coefcient of determination (R2) is about 0.942. The application of Grey Wolf Optimization (GWO) has exhibited notable efectiveness in improving the hyperparameter optimization procedure. The enhanced XGBoost model exhibits noteworthy enhancements in multiple performance metrics. These improvements consist of a reduction in the mean absolute error (MAE) by 0.040, a decrease in the mean squared error (MSE) by 0.005, a decrease in the root-mean-squared error (RMSE) by 0.069, and an increase in the R-squared (R^2) value to 0.997. Upon comparing the observed and predicted values, it becomes apparent that the GWO-optimized model has a greater level of precision and accuracy. This paper presents real-world evidence that supports the idea that creating datasets, doing exploratory analysis, and adjusting hyperparameters are very important for making structural evaluation work well during the design phase. The introduction of improved decision-making processes throughout the product design phase can lead to advancements in the reliability and performance of fxators. Keywords Orthopedic fxator · Structural analysis · Parametric modeling · Finite-element analysis (FEA) · XGBoost · Grey Wolf Optimization (GWO) · Exploratory data analysis (EDA) · Hyperparameter optimization