Towards Time-Evolving Analytics: Online Learning for Time-Dependent Evolving Data Streams

Tracking #: 724-1704

Responsible editor: 

Robert Hoehndorf

Submission Type: 

Position Paper


Traditional historical data analytics is at risk in a world where volatility, uncertainty, complexity, and ambiguity are the new normal. While Streaming Machine Learning (SML) and Time-series Analytics (TSA) attack some aspects of the problem, we are far from a comprehensive solution. SML trains models using fewer data and in a continuous/adaptive way relaxing the assumption that data points are identically distributed. TSA considers temporal dependence among data points, but it assumes identical distribution. Every Data Scientist fights this battle with ad-hoc solutions. In this paper, we claim that, due to the temporal dependence on the data, the existing solutions do not represent robust solutions to efficiently and automatically keep models relevant even when changes occur, and real-time processing is a must. We propose a novel and solid scientific foundation for Time-Evolving Analytics in this perspective. Such a framework aims to develop the logical, methodological, and algorithmic foundations for fast, scalable, and resilient analytics.



  • Reviewed

Data repository URLs: 

Date of Submission: 

Wednesday, July 6, 2022

Date of Decision: 

Wednesday, November 2, 2022

Nanopublication URLs:



Solicited Reviews:

1 Comment

Meta-Review by Editor

The reviewers have provided several suggestions to improve the manuscript. In particular, the clarity of the paper can be improved by clearly introducing the problem that is discussed, introducing technical terms instead of relying on prior knowledge, and removing of jargon; the technical and scientific challenges that need to be addressed should be described more clearly. Additionally, code and data underlying the results shown in the paper should be made available to ensure reprodibility.

Robert Hoehndorf (