Random forest clustering for discrete sequences

Abstract

As one of the most popular machine learning methods, random forests have been successfully applied to different data analysis tasks such as classification, regression and cluster analysis. Recently, the random forest clustering method has received much attention due to its simplicity, accuracy and robustness. However, we cannot directly employ the random forest clustering algorithm to solve the discrete sequence clustering problem because of the lack of explicit features and “negative” sequences. In this paper, we propose a new random forest clustering algorithm for discrete sequences. The proposed method firstly injects a set of decoy sequences and then constructs the random forest in a supervised and adaptive manner by generating features on the fly. Experimental results on real data sets show that the proposed method can achieve better performance than those state-of-the-art discrete sequence clustering algorithms.