Decision Concept Lattice vs. Decision Trees and Random Forests

Decision trees and their ensembles are very popular models of supervised machine learning. In this paper we merge the ideas underlying decision trees, FCA by proposing a new learning model which can be constructed in polynomial time is applicable for both classification regression problems. Specifically, first propose polynomial-time algorithm constructing part concept lattice that based on tree. Second, describe prediction scheme solving tasks with quality comparable to state-of-the-art models.