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

Extreme pricing anomalies may occur unexpectedly without a trivial cause, andequity traders typically experience a meticulous process to source disparateinformation and analyze its reliability before integrating it into the trustedknowledge base. We introduce DeepTrust, a reliable financial knowledgeretrieval framework on Twitter to explain extreme price moves at speed, whileensuring data veracity using state-of-the-art NLP techniques. Our proposedframework consists of three modules, specialized for anomaly detection,information retrieval and reliability assessment. The workflow starts withidentifying anomalous asset price changes using machine learning models trainedwith historical pricing data, and retrieving correlated unstructured data fromTwitter using enhanced queries with dynamic search conditions. DeepTrustextrapolates information reliability from tweet features, traces of generativelanguage model, argumentation structure, subjectivity and sentiment signals,and refine a concise collection of credible tweets for market insights. Theframework is evaluated on two self-annotated financial anomalies, i.e., Twitterand Facebook stock price on 29 and 30 April 2021. The optimal setup outperformsthe baseline classifier by 7.75% and 15.77% on F0.5-scores, and 10.55% and18.88% on precision, respectively, proving its capability in screeningunreliable information precisely. At the same time, information retrieval andreliability assessment modules are analyzed individually on their effectivenessand causes of limitations, with identified subjective and objective factorsthat influence the performance. As a collaborative project with Refinitiv, thisframework paves a promising path towards building a scalable commercialsolution that assists traders to reach investment decisions on pricinganomalies with authenticated knowledge from social media platforms inreal-time.

DeepTrust: A Reliable Financial Knowledge Retrieval Framework For Explaining Extreme Pricing Anomalies