English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Machine learning models play a vital role in time series forecasting. Thesemodels, however, often overlook an important element: point uncertaintyestimates. Incorporating these estimates is crucial for effective riskmanagement, informed model selection, and decision-making.To address thisissue, our research introduces a method for uncertainty estimation. We employ asurrogate Gaussian process regression model. It enhances any base regressionmodel with reasonable uncertainty estimates. This approach stands out for itscomputational efficiency. It only necessitates training one supplementarysurrogate and avoids any data-specific assumptions. Furthermore, this methodfor work requires only the presence of the base model as a black box and itsrespective training data. The effectiveness of our approach is supported byexperimental results. Using various time-series forecasting data, we found thatour surrogate model-based technique delivers significantly more accurateconfidence intervals. These techniques outperform both bootstrap-based andbuilt-in methods in a medium-data regime. This superiority holds across a rangeof base model types, including a linear regression, ARIMA, gradient boostingand a neural network.

Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust