We implement a dynamically regularized, bootstrapped two-stage out-of-sample parametric portfolio policy to evaluate characteristics’ efficacy in the conditional stock return-generating process in the metric of expected power utility. Traditional characteristics, such as momentum and size afforded large utility gains before 1999. These opportunities have since vanished. Overfitting—imprecision in weight estimation—is correlated with the optimal portfolio’s variance. Therefore, it is not a problem for power utility investors with coefficients of relative aversion greater than four. For more risk-tolerant investors, we successfully reduce estimation error by increasing the curvature of the loss function relative to the investor’s utility function.

We argue that mutual fund managers should trade actively only when the market presents opportunities to pick stocks with positive alpha. In this paper, we propose stock-selection opportunity measures and show that a significant portion of mutual funds time their active trading, i.e., they trade more when the market presents more stock-selection opportunities. We show that positive timers outperform negative timers by about 82 bps in annualized four-factor alpha over the subsequent six-month horizon and, more importantly, that stock-selection timing contributes significantly to fund performance even after controlling for fund managers’ stock-picking ability. Finally, we present evidence that on average funds with very high portfolio turnover are actually poor timers, whereas younger funds and funds with larger family size exhibit better skills in timing stock-selection.