An Eager Splitting Strategy for Online Decision Trees

Manapragada, Chaitanya; Gomes, Heitor M; Salehi, Mahsa Baghban; Bifet, Albert; Webb, Geoffrey I.

doi:10.48550/arxiv.2010.10935

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generating synthetic data with various kinds of concept drift is straight-forward through packages like scikit-multiflow [15] or river [16]. A comprehensive collection of synthetic data streams has been proposed by the authors in [45].…”

Section: Finding Real-world Benchmark Data Setsmentioning

confidence: 99%

Standardized Evaluation of Machine Learning Methods for Evolving Data Streams

Haug¹,

Tramountani²,

Kasneci³

2022

Preprint

View full text Add to dashboard Cite

Due to the unspecified and dynamic nature of data streams, online machine learning requires powerful and flexible solutions. However, evaluating online machine learning methods under realistic conditions is difficult. Existing work therefore often draws on different heuristics and simulations that do not necessarily produce meaningful and reliable results. Indeed, in the absence of common evaluation standards, it often remains unclear how online learning methods will perform in practice or in comparison to similar work. In this paper, we propose a comprehensive set of properties for high-quality machine learning in evolving data streams. In particular, we discuss sensible performance measures and evaluation strategies for online predictive modelling, online feature selection and concept drift detection. As one of the first works, we also look at the interpretability of online learning methods. The proposed evaluation standards are provided in a new Python framework called float. Float is completely modular and allows the simultaneous integration of common libraries, such as scikit-multiflow or river, with custom code. Float is open-sourced and can be accessed at https://github.com/haugjo/float. In this sense, we hope that our work will contribute to more standardized, reliable and realistic testing and comparison of online machine learning methods.

show abstract

Section: Finding Real-world Benchmark Data Setsmentioning

confidence: 99%