A healthcare company is developing an ML model using the Amazon SageMaker XGBoost algorithm to classify patients as either high-risk or low-risk for a specific disease. During evaluation, the model performs exceptionally well on the training dataset but fails to accurately classify new patient data. The ML engineer suspects that the model’s performance issues may be related to noise in the dataset and needs to optimize the model to improve its performance on unseen data. As an AWS Certified Machine Learning Engineer Associate, what do you recommend?