Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.03508 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913915663810560 |
|---|---|
| author | Kjærnli, Håkon Hanisch Mas-Ribas, Lluis Håland, Hans Jakob Sjåvik, Vegard Ashrafi, Aida Langseth, Helge Gundersen, Odd Erik |
| author_facet | Kjærnli, Håkon Hanisch Mas-Ribas, Lluis Håland, Hans Jakob Sjåvik, Vegard Ashrafi, Aida Langseth, Helge Gundersen, Odd Erik |
| contents | When deploying time series forecasting models based on machine learning to real world settings, one often encounter situations where the data distribution drifts. Such drifts expose the forecasting models to out-of-distribution (OOD) data, and machine learning models lack robustness in these settings. Robustness can be improved by using deep generative models or genetic algorithms to augment time series datasets, but these approaches lack interpretability and are computationally expensive. In this work, we develop an interpretable and simple framework for generating time series. Our method combines time-series decompositions with analytic functions, and is able to generate time series with characteristics matching both in- and out-of-distribution data. This approach allows users to generate new time series in an interpretable fashion, which can be used to augment the dataset and improve forecasting robustness. We demonstrate our framework through EXPRTS, a visual analytics tool designed for univariate time series forecasting models and datasets. Different visualizations of the data distribution, forecasting errors and single time series instances enable users to explore time series datasets, apply transformations, and evaluate forecasting model robustness across diverse scenarios. We show how our framework can generate meaningful OOD time series that improve model robustness, and we validate EXPRTS effectiveness and usability through three use-cases and a user study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03508 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EXPRTS: Exploring and Probing the Robustness of Time Series Forecasting Models Kjærnli, Håkon Hanisch Mas-Ribas, Lluis Håland, Hans Jakob Sjåvik, Vegard Ashrafi, Aida Langseth, Helge Gundersen, Odd Erik Machine Learning When deploying time series forecasting models based on machine learning to real world settings, one often encounter situations where the data distribution drifts. Such drifts expose the forecasting models to out-of-distribution (OOD) data, and machine learning models lack robustness in these settings. Robustness can be improved by using deep generative models or genetic algorithms to augment time series datasets, but these approaches lack interpretability and are computationally expensive. In this work, we develop an interpretable and simple framework for generating time series. Our method combines time-series decompositions with analytic functions, and is able to generate time series with characteristics matching both in- and out-of-distribution data. This approach allows users to generate new time series in an interpretable fashion, which can be used to augment the dataset and improve forecasting robustness. We demonstrate our framework through EXPRTS, a visual analytics tool designed for univariate time series forecasting models and datasets. Different visualizations of the data distribution, forecasting errors and single time series instances enable users to explore time series datasets, apply transformations, and evaluate forecasting model robustness across diverse scenarios. We show how our framework can generate meaningful OOD time series that improve model robustness, and we validate EXPRTS effectiveness and usability through three use-cases and a user study. |
| title | EXPRTS: Exploring and Probing the Robustness of Time Series Forecasting Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.03508 |