Supervised learning in the presence of concept drift: a modelling framework

Straat, Michiel; Abadi, Fthi; Kan, Zhuoyun; Göpfert, Christina; Hammer, Barbara; Biehl, Michael

doi:10.1007/s00521-021-06035-1

Cited by 9 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such circumstances, the learning system can identify and monitor the perception of drift, i.e., forgetting inappropriate and old information while constantly adjusting to the latest additional contributions. Concept drift has been the subject of previous studies [9,10] looking at its theoretical characteristics and statistical mechanics. This study aims to learn a regression technique that can be used in various situations through practical simulations of scenarios.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED: Continual Learning Approach for Continuous Data Stream Analysis in Dynamic Environments

Prasanna¹,

Khan

Alshahrani

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Continuous data stream analysis primarily focuses on the unanticipated changes in the transmission of data distribution over time. Conceptual change is defined as the signal distribution changes over the transmission of continuous data streams. A drift detection scenario is set forth to develop methods and strategies for detecting, interpreting, and adapting to conceptual changes over data streams. Machine learning approaches can produce poor learning outcomes in the conceptual change environment if the sudden change is not addressed. Furthermore, due to developments in concept drift, learning methodologies have been significantly systematic in recent years. The research introduces a novel approach using the fully connected committee machine (FCM) and different activation functions to address conceptual changes in continuous data streams. It explores scenarios of continual learning and investigates the effects of over-learning and weight decay on concept drift. The findings demonstrate the effectiveness of the FCM framework and provide insights into improving machine learning approaches for continuous data stream analysis. We used a layered neural network framework to experiment with different scenarios of continual learning on continuous data streams in the presence of change in the data distribution using a fully connected committee machine (FCM). In this research, we conduct experiments in various scenarios using a layered neural network framework, specifically the fully connected committee machine (FCM), to address conceptual changes in continuous data streams for continual learning under a conceptual change in the data distribution. Sigmoidal and ReLU (Rectified Linear Unit) activation functions are considered for learning regression in layered neural networks. When the layered framework is trained from the input data stream, the regression scheme changes consciously in all scenarios. A fully connected committee machine (FCM) is trained to perform the tasks described in continual learning with M hidden units on dynamically generated inputs. In this method, we run Monte Carlo simulations with the same number of units on both sides, K and M, to define the advancement of intersections between several hidden units and the calculation of generalization error. This is applied to over-learnability as a method of over-forgetting, integrating weight decay, and examining its effects when a concept drift is presented.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED: Continual Learning Approach for Continuous Data Stream Analysis in Dynamic Environments

Prasanna¹,

Khan

Alshahrani

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The ADO-based hyperparameter tuning procedure [16] is used to find the DNN model's ideal parameters to improve the classifier performance. Liu et al [17] have demonstrated how the current data augmentation techniques either neglect the distribution of data or the spatial relationships among the features.…”

Section: Literature Surveymentioning

confidence: 99%

Concept drift and machine learning model for detecting fraudulent transactions in streaming environment

Shahapurkar¹,

Patil²

2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">In a streaming environment, data is continuously generated and processed in an ongoing manner, and it is necessary to detect fraudulent transactions quickly to prevent significant financial losses. Hence, this paper proposes a machine learning-based approach for detecting fraudulent transactions in a streaming environment, with a focus on addressing concept drift. The approach utilizes the extreme gradient boosting (XGBoost) algorithm. Additionally, the approach employs four algorithms for detecting continuous stream drift. To evaluate the effectiveness of the approach, two datasets are used: a credit card dataset and a Twitter dataset containing financial fraud-related social media data. The approach is evaluated using cross-validation and the results demonstrate that it outperforms traditional machine learning models in terms of accuracy, precision, and recall, and is more robust to concept drift. The proposed approach can be utilized as a real-time fraud detection system in various industries, including finance, insurance, and <br /> e-commerce.</span>

show abstract

“…This is relevant in ML engines that continuously receive newly incoming data to process, which could be set up with health care, education, or consumer data (although admittedly not widely available in social and health sciences research at the time of writing). An example of concept drift over time would be the lowering of predictive power of poverty to explain children’s health when the societal determinants of poverty change over time; see an accessible introduction in ( 33 ) and recent developments in ( 34 ). While most research in the social and health sciences deals with static datasets to date, the importance of this concept will increase with the development of ML engines that continuously process newly incoming data, such as through tracking apps or social network data.…”

Section: Basics Of MLmentioning

confidence: 99%

Mapping of machine learning approaches for description, prediction, and causal inference in the social and health sciences

et al. 2022

View full text Add to dashboard Cite

Machine learning (ML) methodology used in the social and health sciences needs to fit the intended research purposes of description, prediction, or causal inference. This paper provides a comprehensive, systematic meta-mapping of research questions in the social and health sciences to appropriate ML approaches by incorporating the necessary requirements to statistical analysis in these disciplines. We map the established classification into description, prediction, counterfactual prediction, and causal structural learning to common research goals, such as estimating prevalence of adverse social or health outcomes, predicting the risk of an event, and identifying risk factors or causes of adverse outcomes, and explain common ML performance metrics. Such mapping may help to fully exploit the benefits of ML while considering domain-specific aspects relevant to the social and health sciences and hopefully contribute to the acceleration of the uptake of ML applications to advance both basic and applied social and health sciences research.

show abstract

Supervised learning in the presence of concept drift: a modelling framework

Cited by 9 publications

References 45 publications

RETRACTED: Continual Learning Approach for Continuous Data Stream Analysis in Dynamic Environments

RETRACTED: Continual Learning Approach for Continuous Data Stream Analysis in Dynamic Environments

Concept drift and machine learning model for detecting fraudulent transactions in streaming environment

Mapping of machine learning approaches for description, prediction, and causal inference in the social and health sciences

Contact Info

Product

Resources

About