Quant BuffetRelax, Not Over Thinking

Empirical Asset Pricing via Machine Learning

Log in to collect

Academic paper

to Open PDF]

AuthorsMeb Faber

Institute
  • Institut Mines-Télécom Business School
  • ?Cambria Investment Management

Strategy in a nutshell

The strategy uses machine learning to forecast one-month-ahead excess returns for 71 country stock markets from 1985–2021. Multiple models—including OLS, LASSO, RF, GBRT, and neural networks—predict returns using 88 market characteristics. Markets are ranked monthly, sorted into quintiles, and an equal-weighted long-short hedge portfolio is formed by going long on top-predicted markets and short on the lowest, with monthly rebalancing.

Economic rationale

The strategy’s success stems mainly from market mispricing rather than risk. Limits to arbitrage, illiquidity in small/emerging markets, and behavioral biases create exploitable anomalies. Combining multiple machine learning models enhances prediction stability and captures statistically significant abnormal returns..

Backtest performance

Annualised return21.55%
Volatility14.3%
Sharpe ratio1.37
Maximum drawdown-36%