Handling Concept Drifts in Regression Problems – the Error Intersection Approach

Bibtex

Cite as text

						@Select Types{,
							 
							 
							 
							 
							 
							Journal   = "Band-1",
							 Title= "Handling Concept Drifts in Regression Problems – the Error Intersection Approach", 
							Author= "Lucas Baier, Marcel Hofmann, Niklas Kühl, Marisa Mohr and Gerhard Satzger", 
							Doi= "https://doi.org/10.30844/wi_2020_c1-baier", 
							 Abstract= "Machine learning models are omnipresent for predictions on big data. One challenge of deployed models is the change of the data over time—a phenomenon called concept drift. If not handled correctly, a concept drift can lead to significant mispredictions. We explore a novel approach for concept drift handling, which depicts a strategy to switch between the application of simple and complex machine learning models for regression tasks. We assume that the approach plays out the individual strengths of each model, switching to the simpler model if a drift occurs and switching back to the complex model for typical situations. We instantiate the approach on a real-world data set of taxi demand in New York City, which is prone to multiple drifts, e.g. the weather phenomena of blizzards, resulting in a sudden decrease of taxi demand. We are able to show that our suggested approach outperforms all regarded baselines significantly.

", 
							 Keywords= "Machine learning, Concept drift, Demand Prediction", 
							}
					
Lucas Baier, Marcel Hofmann, Niklas Kühl, Marisa Mohr and Gerhard Satzger: Handling Concept Drifts in Regression Problems – the Error Intersection Approach. Online: https://doi.org/10.30844/wi_2020_c1-baier (Abgerufen 20.08.22)

Abstract

Abstract

Machine learning models are omnipresent for predictions on big data. One challenge of deployed models is the change of the data over time—a phenomenon called concept drift. If not handled correctly, a concept drift can lead to significant mispredictions. We explore a novel approach for concept drift handling, which depicts a strategy to switch between the application of simple and complex machine learning models for regression tasks. We assume that the approach plays out the individual strengths of each model, switching to the simpler model if a drift occurs and switching back to the complex model for typical situations. We instantiate the approach on a real-world data set of taxi demand in New York City, which is prone to multiple drifts, e.g. the weather phenomena of blizzards, resulting in a sudden decrease of taxi demand. We are able to show that our suggested approach outperforms all regarded baselines significantly.

Keywords

Schlüsselwörter

Machine learning, Concept drift, Demand Prediction

References

Referenzen

Leider ist der Eintrag nur auf Amerikanisches Englisch verfügbar.

Most viewed articles

Meist angesehene Beiträge

GITO events | library.gito