M Kishore Kumar 01 02 The concept drift or the change in the data distribution hinders the sustainability of the accuracy ofmachine learning models greatly in dynamic conditions In this work an ensemblebased method of successfuldetection and adaptation of drifts of ideas is proposed The proposed approach employs a range of classifiers tomonitor decreases in the performance and relies on the trend in disagreement or accuracy to detect drift The ensembleis adaptive as it retrains or replaces affected models in a case of drift to ensure continued reliability Both theartificial and realworld data on both test sets indicate that unlike the traditional single model solutions our approachdelivers a high level of robust classifications and increased sensitivity of the detection This methodology is well suitedto applications in streaming data where the drift needs to be detected very quickly and accurately to be used in adecisionmaking system Copyright (c) International Journal of Engineering and Basic Sciences. All rights reserved 2026