We investigate the stock return volatility predictability using firm’s fundamental risk with machine learning … fundamental risk in forecasting future volatility. The nonlinear models, especially the neural networks, outperform the linear … types. Firms with high expected volatility have higher fundamental risk and commonality in fundamental characteristics …

fairly priced stocks. Thus, our results support the mispricing and arbitrage risk hypotheses that the positive (negative …

suggest that the hedge fund strategies' betas respond more to illiquidity uncertainty than to illiquidity risk during crises … systematic risk is highly nonlinear in extreme scenarios-especially during the subprime crisis. We find that countercyclical …-traditional risk premia by deliberately increasing their systematic risk while the later focus more on minimizing risk. Our results …

We give an explicit algorithm and source code for constructing risk models based on machine learning techniques. The … learning risk models to other constructions, including statistical risk models, risk models based on fundamental industry …

We develop a measure of how information events impact investors' perceptions of risk that is broadly applicable and … simultaneously conveys information on the announcer's expected future cash flows and risk profile. We empirically implement the … forecasting power for firms' risk-factor exposures, implied costs of capital, liquidity, and future investments. We also apply our …

This paper examines the relationship between idiosyncratic risk and stock returns in BRICS (Brazil, Russia, India … risk puzzle by dividing firms into groups based on fundamentals, such as their market risk, financial constraints, and … liquidity position. Finally, it investigates whether the idiosyncratic risk is priced in BRICS countries’ equity markets. The …

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 …-low portfolio yields 2.52% (1.48%). Existing OOS inferences do not account for ex-ante estimation uncertainty and thus are not …

after controlling for transaction costs, liquidity, and bond characteristics. We also propose new risk factors based on the …