Breast Cancer Classification Using Naïve Bayes and Random Forest Algorithms

Abstract

Breast cancer is one of the leading causes of death among women in Indonesia. Therefore, early detection is crucial to improving the chances of successful treatment. This study was conducted to evaluate the performance differences between the Naïve Bayes and Random Forest algorithms in classifying breast cancer data. The dataset used was sourced from Kaggle, and the entire data processing and model analysis process was performed using RapidMiner software. Data was split into 80% for training and 20% for testing to ensure optimal model evaluation. Evaluation was conducted using accuracy, precision, and recall metrics. The findings of this study indicate that Random Forest is capable of producing more effective classification performance than Naïve Bayes. Random Forest achieved an accuracy of 99.27%, recall of 99.27%, and precision of 99.30%. Meanwhile, the Naïve Bayes algorithm only achieved an accuracy of 83.78% with recall and precision of 83.80% each. The superiority of Random Forest is believed to stem from its ensemble approach, which can handle data complexity and reduce the risk of overfitting, thereby providing more accurate and stable prediction results. Based on these results, Random Forest is considered more suitable for use in machine learning-based early breast cancer detection systems. This study is expected to serve as a reference for the development of medical decision support systems and to encourage the use of classification technology in the field of health.