Working Paper: NBER ID: w23933
Authors: Alexander M. Chinco; Adam D. Clark-Joseph; Mao Ye
Abstract: This paper applies the Least Absolute Shrinkage and Selection Operator (LASSO) to make rolling 1-minute-ahead return forecasts using the entire cross section of lagged returns as candidate predictors. The LASSO increases both out-of-sample fit and forecast-implied Sharpe ratios. And, this out-of-sample success comes from identifying predictors that are unexpected, short-lived, and sparse. Although the LASSO uses a statistical rule rather than economic intuition to identify predictors, the predictors it identifies are nevertheless associated with economically meaningful events: the LASSO tends to identify as predictors stocks with news about fundamentals.
Keywords: LASSO; stock returns; forecasting; predictability
JEL Codes: C55; C58; G12; G14
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| LASSO (C20) | out-of-sample fit (C52) |
| LASSO (C20) | forecast-implied Sharpe ratios (G17) |
| LASSO (C20) | predictive accuracy (C52) |
| predictors identified by LASSO (C52) | stock returns (G12) |