|Drift Detection Method (DDM) emerges as a critical problem faced in the In-dustry 4.0 era, especially for the identification of concept drift in continuously-gathered data streams. In this study, a small-scale comparison with regard to the impact of different classifiers in DDM is presented. Six well-established classi-fiers are introduced in order to compare their performance and evaluate their impact on DDM, namely Naïve Bayes (NB), Hoeffding Tree (HT), k-Nearest Neighbors (KNN), Passive Aggressive (PAC), Stochastic Gradient Descent (SGD) and Very Fast Decision Rules (VFDRC) classifiers. Streaming Ensem-ble Algorithm (SEA dataset) was selected to validate our simulations due to its suitability regarding concept drift detection and handling, incorporating abrupt concept changes. Confusion matrices were used to effectively juxtapose the per-formance of the considered algorithms in the SEA dataset. The findings suggest that KNN exhibits the best overall accuracy (87%) and seems to be the most stable algorithm compared to NB (86%), HT (86%) and VFDRC (84%) classi-fiers. Overall, these algorithms show increased performance, while the presence of noise in the data has a significant impact on the model accuracy.|
*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.