Alternative beta strategies often exhibit high performance in hypothetical backtests, but their live actual performance can be substantially less than projected by investment banks (most especially in equity value strategies). "Factor fishing" and data mining allow the construction of products that perform well in historical backtests, but not as well live.
SUHONEN, A., LENNKH, M., & PEREZ, F. (2017). Quantifying Backtest Overfitting in Alternative Beta Strategies. Journal Of Portfolio Management, 43(2), 90-104.
No comments:
Post a Comment