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

Multimodal analysis that uses numerical time series and textual corpora asinput data sources is becoming a promising approach, especially in thefinancial industry. However, the main focus of such analysis has been onachieving high prediction accuracy while little effort has been spent on theimportant task of understanding the association between the two datamodalities. Performance on the time series hence receives little explanationthough human-understandable textual information is available. In this work, weaddress the problem of given a numerical time series, and a general corpus oftextual stories collected in the same period of the time series, the task is totimely discover a succinct set of textual stories associated with that timeseries. Towards this goal, we propose a novel multi-modal neural model calledMSIN that jointly learns both numerical time series and categorical textarticles in order to unearth the association between them. Through multiplesteps of data interrelation between the two data modalities, MSIN learns tofocus on a small subset of text articles that best align with the performancein the time series. This succinct set is timely discovered and presented asrecommended documents, acting as automated information filtering, for the giventime series. We empirically evaluate the performance of our model ondiscovering relevant news articles for two stock time series from Apple andGoogle companies, along with the daily news articles collected from the ThomsonReuters over a period of seven consecutive years. The experimental resultsdemonstrate that MSIN achieves up to 84.9% and 87.2% in recalling the groundtruth articles respectively to the two examined time series, far more superiorto state-of-the-art algorithms that rely on conventional attention mechanism indeep learning.

"The Squawk Bot": Joint Learning of Time Series and Text Data Modalities for Automated Financial Information Filtering