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/

Global: Zendy Tools annual

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

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We enhance the accuracy and generalization of univariate time series pointprediction by an explainable ensemble on the fly. We propose an InterpretableDynamic Ensemble Architecture (IDEA), in which interpretable base learners givepredictions independently with sparse communication as a group. The model iscomposed of several sequentially stacked groups connected by group backcastresiduals and recurrent input competition. Ensemble driven by end-to-endtraining both horizontally and vertically brings state-of-the-art (SOTA)performances. Forecast accuracy improves by 2.6% over the best statisticalbenchmark on the TOURISM dataset and 2% over the best deep learning benchmarkon the M4 dataset. The architecture enjoys several advantages, being applicableto time series from various domains, explainable to users with specializedmodular structure and robust to changes in task distribution.

IDEA: Interpretable Dynamic Ensemble Architecture for Time Series Prediction