The More, the Better? Predicting Stock Returns with Local and Global Data

Cakici, Nusret; Zaremba, Adam

The More, the Better? Predicting Stock Returns with Local and Global Data

Abstract

We investigate the utility of local and global data in cross-sectional asset pricing. Using machine learning and three decades of stock data from 45 markets, we evaluate the performance of locally and globally trained models across country, regional, sector, and industry dimensions. We find limited added value in global over local data, as both yield comparable predictive performance. The gains from global training are uneven and mainly benefit smaller markets with high idiosyncratic risk. Stock return drivers are broadly consistent across markets, with global alignment in asset pricing increasing over time. Thus, local data is typically sufficient for accurate return forecasting, with incremental benefits of global datasets likely diminishing over time.

Keywords

asset pricing return predictability market integration financial integration machine learning elastic net cross-section of stock returns international stock markets transfer learning factor zoo local vs. global models

Citation

Cakici, N., & Zaremba, A. (2026). The more, the better? Predicting stock returns with local and global data. Journal of Banking & Finance, 186, 107658.

URI

https://open.icm.edu.pl/handle/123456789/26647

Belongs to collection

Artykuły / Articles

Full item record