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/

Zendy Plus

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

Zendy Tools

Zendy Open

This study presents a groundbreaking model for forecasting long-termfinancial time series, termed the Enhanced LFTSformer. The model distinguishesitself through several significant innovations:  (1) VMD-MIC+FE Feature Engineering: The incorporation of sophisticatedfeature engineering techniques, specifically through the integration ofVariational Mode Decomposition (VMD), Maximal Information Coefficient (MIC),and feature engineering (FE) methods, enables comprehensive perception andextraction of deep-level features from complex and variable financial datasets.(2) DS Encoder Informer: The architecture of the original Informer has beenmodified by adopting a Stacked Informer structure in the encoder, and aninnovative introduction of a multi-head decentralized sparse attentionmechanism, referred to as the Distributed Informer. This modification has ledto a reduction in the number of attention blocks, thereby enhancing both thetraining accuracy and speed. (3) GC Enhanced Adam \& Dynamic Loss Function: Thedeployment of a Gradient Clipping-enhanced Adam optimization algorithm and adynamic loss function represents a pioneering approach within the domain offinancial time series prediction. This novel methodology optimizes modelperformance and adapts more dynamically to evolving data patterns.  Systematic experimentation on a range of benchmark stock market datasetsdemonstrates that the Enhanced LFTSformer outperforms traditional machinelearning models and other Informer-based architectures in terms of predictionaccuracy, adaptability, and generality. Furthermore, the paper identifiespotential avenues for future enhancements, with a particular focus on theidentification and quantification of pivotal impacting events and news. This isaimed at further refining the predictive efficacy of the model.

Enhanced LFTSformer: A Novel Long-Term Financial Time Series Prediction  Model Using Advanced Feature Engineering and the DS Encoder Informer  Architecture