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

Neural networks have revolutionized many empirical fields, yet theirapplication to financial time series forecasting remains controversial. In thisstudy, we demonstrate that the conventional practice of estimating modelslocally in data-scarce environments may underlie the mixed empiricalperformance observed in prior work. By focusing on volatility forecasting, weemploy a dataset comprising over 10,000 global stocks and implement a globalestimation strategy that pools information across cross-sections. Oureconometric analysis reveals that forecasting accuracy improves markedly as thetraining dataset becomes larger and more heterogeneous. Notably, even with aslittle as 12 months of data, globally trained networks deliver robustpredictions for individual stocks and portfolios that are not even in thetraining dataset. Furthermore, our interpretation of the model dynamics showsthat these networks not only capture key stylized facts of volatility but alsoexhibit resilience to outliers and rapid adaptation to market regime changes.These findings underscore the importance of leveraging extensive and diversedatasets in financial forecasting and advocate for a shift from traditionallocal training approaches to integrated global estimation methods.

Global Neural Networks and The Data Scaling Effect in Financial Time Series Forecasting