Global Neural Networks and The Data Scaling Effect in Financial Time Series Forecasting
This addresses the problem of unreliable financial forecasting for investors and analysts by proposing a shift from local to global methods, though it is incremental as it builds on existing neural network applications.
The study tackled the mixed performance of neural networks in financial time series forecasting by showing that global estimation with pooled data from over 10,000 stocks improves accuracy, achieving robust predictions even with only 12 months of data.
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.