Panel Data Nowcasting: The Case of Price-Earnings Ratios

TL;DR

This paper introduces a structured machine learning approach using sparse-group LASSO for nowcasting price-earnings ratios with panel data sampled at different frequencies, outperforming traditional methods.

Contribution

It develops a novel application of sparse-group LASSO regularization to mixed-frequency panel data for nowcasting financial ratios, demonstrating improved predictive performance.

Findings

Machine learning panel regressions outperform analysts' predictions.

Sparse-group LASSO effectively leverages mixed-frequency data.

Models show superior accuracy over standard methods.

Abstract

The paper uses structured machine learning regressions for nowcasting with panel data consisting of series sampled at different frequencies. Motivated by the problem of predicting corporate earnings for a large cross-section of firms with macroeconomic, financial, and news time series sampled at different frequencies, we focus on the sparse-group LASSO regularization which can take advantage of the mixed frequency time series panel data structures. Our empirical results show the superior performance of our machine learning panel data regression models over analysts' predictions, forecast combinations, firm-specific time series regression models, and standard machine learning methods.