Hyper-Parameter optimization is crucial for improving machine learning algorithms. A new method called Randomized-Hyperopt was introduced to tune the hyperparameters of the XGBoost algorithm. The study compared Randomized-Hyperopt with other common methods like Random search, Hyperopt, and Grid Search. Results showed that Randomized-Hyperopt outperformed the other methods in terms of both prediction accuracy and execution time when optimizing XGBoost hyperparameters.