Return Predictability and Market-Timing: A One-Month Model

Abstract

We propose a one-month market-timing model constructed from 15 diverse variables. We use weighted least squares with stepwise variable selection to build a predictive model for the one-month-ahead market excess returns. From our statistical model, we transform our forecasts into investable positions to build a market-timing strategy. From 2003 to 2017, our strategy results in 16.6% annual returns with a 0.92 Sharpe ratio and a 20.3% maximum drawdown, whereas the S&P 500 has annual returns of 10%, a 0.46 Sharpe ratio, and a maximum drawdown of 55.2%. When our one-month model is used in conjunction with Hull and Qiao’s (2017) six-month model, the Sharpe ratio of the combined strategy exceeds the individual model Sharpe ratios. The combined model has 15% annual returns, a Sharpe ratio of 1.12, and a maximum drawdown of 14%. We publish forecasts from our one-month model in our Daily Report.

Keywords: equity premium, forecasting, predictability, market timing, asset returns, tactical asset allocation