This paper derives ex-ante standard errors of risk premium predictions from neural networks (NNs). Considering standard … that have precise risk premia earns an OOS average monthly return of 3.61% (2.21%). In contrast, the conventional high … financial shocks. In the cross-section, the level and precision of risk premia are correlated, thus NN-based investments deliver …

equity premium to invest in risky assets. However, once she does invest because of a large risk premium, she becomes …

so doing, we bring two strands of the exchange rate literature, namely market-microstructure and risk-based models … carry trading and momentum strategies. We find that they appear to be good proxies for currency crash risk. Additionally, we … the foreign exchange market. In particular, it appears that financial customers are risk takers in the market, while non …