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

TL;DR

This paper shows that globally trained neural networks using large, diverse datasets significantly improve financial time series forecasting accuracy, even with limited data, by capturing key market features and adapting to changes.

Contribution

It introduces a global estimation approach for neural networks in financial forecasting, demonstrating its superiority over local models in terms of accuracy and robustness.

Findings

Forecasting accuracy improves with larger, more heterogeneous datasets.

Global models perform well even with limited data (12 months).

Networks capture stylized facts and adapt to market regime changes.

Abstract

Neural networks have revolutionized many empirical fields, yet their application to financial time series forecasting remains controversial. In this study, we demonstrate that the conventional practice of estimating models locally in data-scarce environments may underlie the mixed empirical performance observed in prior work. By focusing on volatility forecasting, we employ a dataset comprising over 10,000 global stocks and implement a global estimation strategy that pools information across cross-sections. Our econometric analysis reveals that forecasting accuracy improves markedly as the training dataset becomes larger and more heterogeneous. Notably, even with as little as 12 months of data, globally trained networks deliver robust predictions for individual stocks and portfolios that are not even in the training dataset. Furthermore, our interpretation of the model dynamics shows that these networks not only capture key stylized facts of volatility but also exhibit resilience to outliers and rapid adaptation to market regime changes. These findings underscore the importance of leveraging extensive and diverse datasets in financial forecasting and advocate for a shift from traditional local training approaches to integrated global estimation methods.