This study investigates the impact of hyperparameter tuning on the accuracy of Support Vector
Machines (SVMs), focusing on the comparison between three widely used tuning techniques: Grid
Search, Random Search, and Bayesian Optimization. SVMs are highly sensitive to hyperparameters
such as the regularization parameter (C) and gamma, which significantly influence the model's ability
to generalize from training data. Through a series of experiments, we evaluate the effectiveness of
each tuning method in optimizing these parameters to enhance model performance. Our results show
that Bayesian Optimization consistently outperforms both Grid Search and Random Search in terms of
accuracy, while also being more computationally efficient. These findings highlight the importance of
selecting appropriate tuning strategies in machine learning workflows, especially in applications where
model accuracy and computational efficiency are critical.
