RFAE: Autoencoding Random Forests

Autoencoding Random Forests ('RFAE') provide a method to autoencode mixed-type tabular data using Random Forests ('RF'), which involves projecting the data to a latent feature space of user-chosen dimensionality (usually a lower dimension), and then decoding the latent representations back into the input space. The encoding stage is useful for feature engineering and data visualisation tasks, akin to how principal component analysis ('PCA') is used, and the decoding stage is useful for compression and denoising tasks. At its core, 'RFAE' is a post-processing pipeline on a trained random forest model. This means that it can accept any trained RF of 'ranger' object type: 'RF', 'URF' or 'ARF'. Because of this, it inherits Random Forests' robust performance and capacity to seamlessly handle mixed-type tabular data. For more details, see Vu et al. (2025) .