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

Time series forecasting is widely used in business intelligence, e.g.,forecast stock market price, sales, and help the analysis of data trend. Mosttime series of interest are macroscopic time series that are aggregated frommicroscopic data. However, instead of directly modeling the macroscopic timeseries, rare literature studied the forecasting of macroscopic time series byleveraging data on the microscopic level. In this paper, we assume that themicroscopic time series follow some unknown mixture probabilisticdistributions. We theoretically show that as we identify the ground truthlatent mixture components, the estimation of time series from each componentcould be improved because of lower variance, thus benefitting the estimation ofmacroscopic time series as well. Inspired by the power of Seq2seq and itsvariants on the modeling of time series data, we propose Mixture of Seq2seq(MixSeq), an end2end mixture model to cluster microscopic time series, whereall the components come from a family of Seq2seq models parameterized bydifferent parameters. Extensive experiments on both synthetic and real-worlddata show the superiority of our approach.

MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data