We assess financial theory-based and machine learning-implied measurements of stock risk premia by comparing the … preferable to rely on a theory-based approach instead of engaging in the computerintensive hyper-parameter tuning of statistical … models. The theory-based approach also delivers a solid performance at the one year horizon, at which only one machine …

specifications based on Expected Utility Theory and theory drawn from behavioural finance. We assess whether machine learning can … findings suggest that machine learning methods provide more accurate models of stock returns based on risk factors than … standard regression-based methods of estimation. They also indicate that certain risk factors and combinations of risk factors …

predictable loan fees in order to mitigate the risk of unexpected loan fee increases. I present evidence that loan demand is the …

A large set of macroeconomic variables have been suggested as equity risk premium predictors in the literature. This … paper proposes a forecasting approach for the equity risk premium with two novel features. First, individual month … robust to sub-period analyses, expanding versus rolling estimation windows, and different investors' risk aversion levels …

This paper derives ex-ante (co)variances of stock-level and portfolio-level risk premium predictions from neural … networks (NNs). Based on the precision of risk premium forecasts, I provide improved investment strategies. The confident high …-low strategies that take long-short positions exclusively on stocks with precise risk premium forecasts deliver superior out …

This paper proposes a flexible but parsimonious specification of the joint dynamics of market risk and return to …

-based ex-post measures of macroeconomic risk. Inflation uncertainty is an important driver of bond premia, but the relation …