Learners Reliability Estimated Through Neural Networks Applied to Build a Novel Hybrid Ensemble Method

In this paper a novel hybrid ensemble method aiming at the improvement of models accuracy in regression tasks is presented. The basic idea of the approach is the creation of an ensemble learner composed by a strong learner which is trained by exploiting data belonging to the whole training dataset and a set of specialised weak learners trained by using data coming from limited regions of the input space determined by means of a self organising map based clustering. In this context, different methods have been tested for the design of the learners, including a hierarchical approach. In the simulation phase, the strong and weak learners operate according to their punctual self-estimated reliabilities so as to exploit their strengths and overcome their weaknesses. The method has been tested on literature and real world datasets achieving competitive results by outperforming other ensemble methods on most of the tested datasets and reducing the average absolute error by up to 10%.