Understanding random forests and overfitting: a visualization and simulation study

arXiv:2402.18612v1 Announce Type: cross
Abstract: Random forests have become popular for clinical risk prediction modelling. In a case study on predicting ovarian malignancy, we observed training c-statistics close to 1. Although this suggests overfitting, performance was competitive on test data. We aimed to understand the behaviour of random forests by (1) visualizing data space in three real world case studies and (2) a simulation study. For the case studies, risk estimates were visualised using heatmaps in a 2-dimensional subspace. The …

abstract arxiv become case case study clinical cs.cy cs.lg data forests modelling overfitting performance popular prediction random random forests risk simulation statistics stat.me study test training type understanding visualization