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

Financial time-series forecasting is one of the most challenging domains inthe field of time-series analysis. This is mostly due to the highlynon-stationary and noisy nature of financial time-series data. With progressiveefforts of the community to design specialized neural networks incorporatingprior domain knowledge, many financial analysis and forecasting problems havebeen successfully tackled. The temporal attention mechanism is a neural layerdesign that recently gained popularity due to its ability to focus on importanttemporal events. In this paper, we propose a neural layer based on the ideas oftemporal attention and multi-head attention to extend the capability of theunderlying neural network in focusing simultaneously on multiple temporalinstances. The effectiveness of our approach is validated using large-scalelimit-order book market data to forecast the direction of mid-price movements.Our experiments show that the use of multi-head temporal attention modulesleads to enhanced prediction performances compared to baseline models.

Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series prediction