Using inductive conformal martingales for addressing concept drift in data stream classification

Charalambos Eliades, Harris Papadopoulos
Proceedings of the Tenth Symposium on Conformal and Probabilistic Prediction and Applications, PMLR 152:171-190, 2021.

Abstract

In this paper, we investigate the use of Inductive Conformal Martingales (ICM) with the histogram betting function for detecting the occurrence of concept drift (CD) in data stream classification. A change in the data distribution will almost surely affect the performance of our classification model resulting in false predictions. Therefore, a reliable and fast detection of the point at which a CD occurs, allows effective retraining of the model to recover accuracy. Our approach is based on ICM with the histogram betting function, which is much more computationally efficient than alternative ICM approaches. To accelerate the process of detecting CD we also modify the ICM and examine different parameters of the histogram betting function. We evaluate the proposed approach on three benchmark datasets, namely STAGGER, SEA and ELEC, presenting different measures of its performance and comparing it with existing methods in the literature.

Cite this Paper

BibTeX
@InProceedings{pmlr-v152-eliades21a, title = {Using inductive conformal martingales for addressing concept drift in data stream classification}, author = {Eliades, Charalambos and Papadopoulos, Harris}, booktitle = {Proceedings of the Tenth Symposium on Conformal and Probabilistic Prediction and Applications}, pages = {171--190}, year = {2021}, editor = {Carlsson, Lars and Luo, Zhiyuan and Cherubin, Giovanni and An Nguyen, Khuong}, volume = {152}, series = {Proceedings of Machine Learning Research}, month = {08--10 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v152/eliades21a/eliades21a.pdf}, url = {https://proceedings.mlr.press/v152/eliades21a.html}, abstract = {In this paper, we investigate the use of Inductive Conformal Martingales (ICM) with the histogram betting function for detecting the occurrence of concept drift (CD) in data stream classification. A change in the data distribution will almost surely affect the performance of our classification model resulting in false predictions. Therefore, a reliable and fast detection of the point at which a CD occurs, allows effective retraining of the model to recover accuracy. Our approach is based on ICM with the histogram betting function, which is much more computationally efficient than alternative ICM approaches. To accelerate the process of detecting CD we also modify the ICM and examine different parameters of the histogram betting function. We evaluate the proposed approach on three benchmark datasets, namely STAGGER, SEA and ELEC, presenting different measures of its performance and comparing it with existing methods in the literature.} }
Endnote
%0 Conference Paper %T Using inductive conformal martingales for addressing concept drift in data stream classification %A Charalambos Eliades %A Harris Papadopoulos %B Proceedings of the Tenth Symposium on Conformal and Probabilistic Prediction and Applications %C Proceedings of Machine Learning Research %D 2021 %E Lars Carlsson %E Zhiyuan Luo %E Giovanni Cherubin %E Khuong An Nguyen %F pmlr-v152-eliades21a %I PMLR %P 171--190 %U https://proceedings.mlr.press/v152/eliades21a.html %V 152 %X In this paper, we investigate the use of Inductive Conformal Martingales (ICM) with the histogram betting function for detecting the occurrence of concept drift (CD) in data stream classification. A change in the data distribution will almost surely affect the performance of our classification model resulting in false predictions. Therefore, a reliable and fast detection of the point at which a CD occurs, allows effective retraining of the model to recover accuracy. Our approach is based on ICM with the histogram betting function, which is much more computationally efficient than alternative ICM approaches. To accelerate the process of detecting CD we also modify the ICM and examine different parameters of the histogram betting function. We evaluate the proposed approach on three benchmark datasets, namely STAGGER, SEA and ELEC, presenting different measures of its performance and comparing it with existing methods in the literature.
APA
Eliades, C. & Papadopoulos, H.. (2021). Using inductive conformal martingales for addressing concept drift in data stream classification. Proceedings of the Tenth Symposium on Conformal and Probabilistic Prediction and Applications, in Proceedings of Machine Learning Research 152:171-190 Available from https://proceedings.mlr.press/v152/eliades21a.html.

Related Material