Optimizing Machine Learning Models for Breast Cancer Prediction: A Comparative Study of Advanced Hyperparameter Tuning Techniques

Breast cancer is a major health problem worldwide, where finding it early can help patients recover better and spend less on treatment. Machine learning has helped healthcare by improving how well doctors can find and care for patients. However, changing certain model settings (hyperparameters) can strongly affect how well these computer models predict breast cancer. This study uses a public dataset (the UCI Breast Cancer Dataset) to compare different approaches to fine-tuning these settings for models predicting breast cancer early. The goal is to guide doctors and data scientists in choosing fine-tuning methods by comparing models based on their accuracy and reliability.