Maximum Depth Parameter Explorations of Random Forest Method For Breast Cancer Classification On RNA Mutations Data

One kind of cancer that affects women globally is breast cancer. Machine learning techniques are a possible alternative approach to increase the precision of breast cancer detection. One popular technique that can handle the complexity of genetic data is Random Forest. The purpose of this study is to investigate how changes in the maximum depth parameter affect the Random Forest method’s ability to classify breast cancer using RNA mutations data. This study uses METABRIC RNA Mutations dataset that is processed through feature selection process to ensure the most relevant features for classification. Experiments were conducted by applying various maximum depth values to the Random Forest model and measuring its performance in terms of accuracy, precision, recall, and F1-score. The results showed that variations in the maximum depth parameter had a significant effect on model performance, where the optimal maximum depth value can substantially increase classification accuracy. These findings provide valuable insights into the use of Random Forest for breast cancer classification, especially in setting appropriate parameters to improve prediction accuracy based on gene expression.