Quant BuffetRelax, Not Over Thinking

The High Resolution Term Structure of Stock Return Predictability

Log in to collect

Academic paper

The High Resolution Term Structure of Stock Return Predictability

AuthorsSpyros Skouras

Institute
  • GRAthens University of Economics and Business
  • ?Athens University of Economics and Business - Department of International and European Economic Studies

Strategy in a nutshell

The HiRes trading strategy invests in US common stocks listed on NYSE, Amex, or NASDAQ. It uses an AR-Midas model with 1600 daily lags to forecast monthly returns, ranks stocks into deciles, and forms value-weighted long-short portfolios. The strategy buys top-decile stocks and shorts bottom-decile stocks, with monthly rebalancing, leveraging out-of-sample forecasts to generate predictable returns.

Economic rationale

High-resolution term structure analysis allows precise modeling of return dynamics. By capturing daily return information over long horizons, the AR-Midas forecasts exploit predictability in stock returns, enhancing portfolio selection and improving risk-adjusted performance.

Backtest performance

Annualised return18.3%
Volatility22.06%
Sharpe ratio0.83