Adaptive Decision Forest: An incremental machine learning framework

In this study, we present an incremental machine learning framework called Adaptive Decision Forest (ADF), which produces a decision forest to classify new records. Based on our two novel theorems, introduce splitting strategy iSAT, allows ADF records even if they are associated with previously unseen classes. is capable of identifying and handling concept drift; it, however, does not forget gained knowledge. Moreover, big data the can be divided into batches. We evaluate nine publicly available natural datasets one synthetic dataset, compare performance against eight state-of-the-art techniques. also examine effectiveness in some challenging situations. Our experimental results, including statistical sign test Nemenyi analyses, indicate clear superiority proposed over