A0327
Title: Panel data nowcasting: The Case of price-earnings ratios
Authors: Eric Ghysels - University of North Carolina Chapel Hill (United States) [presenting]
Andrii Babii - University of North Carolina (United States)
Jonas Striaukas - Copenhagen Business School (Denmark)
Ryan Ball - University of Michigan (United States)
Abstract: The proposed method 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, the method focuses on the sparse-group LASSO regularization, which can take advantage of the mixed-frequency time series panel data structures. The empirical results show the superior performance of the machine learning panel data regression models over analysts' predictions, forecast combinations, firm-specific time series regression models, and standard machine learning methods.
