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 Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Developing models and algorithms to predict nonstationary time series is along standing statistical problem. It is crucial for many applications, inparticular for fashion or retail industries, to make optimal inventorydecisions and avoid massive wastes. By tracking thousands of fashion trends onsocial media with state-of-the-art computer vision approaches, we propose a newmodel for fashion time series forecasting. Our contribution is twofold. Wefirst provide publicly a dataset gathering 10000 weekly fashion time series. Asinfluence dynamics are the key of emerging trend detection, we associate witheach time series an external weak signal representing behaviours ofinfluencers. Secondly, to leverage such a dataset, we propose a new hybridforecasting model. Our approach combines per-time-series parametric models withseasonal components and a global recurrent neural network to include sporadicexternal signals. This hybrid model provides state-of-the-art results on theproposed fashion dataset, on the weekly time series of the M4 competition, andillustrates the benefit of the contribution of external weak signals.

HERMES: Hybrid Error-corrector Model with inclusion of External Signals for nonstationary fashion time series