How should you discount your backtest PnL?

2019/02/05 by Rej, Adam, Seager, Philip, Bouchaud, Jean-Philippe
#FOS: Economics and business #Statistical Finance (q-fin.ST)

paper · doi:10.48550/arxiv.1902.01802

Abstract

In-sample overfitting is a drawback of any backtest-based investment strategy. It is thus of paramount importance to have an understanding of why and how the in-sample overfitting occurs. In this article we propose a simple framework that allows one to model and quantify in-sample PnL overfitting. This allows us to compute the factor appropriate for discounting PnLs of in-sample investment strategies.

Related

• Avoiding Backtesting Overfitting by Covariance-Penalties: an empirical\n investigation of the ordinary and total least squares cases
• In-Sample and Out-of-Sample Sharpe Ratios for Linear Predictive Models
• Pseudo-Mathematics and Financial Charlatanism: The Effects of Backtest Overfitting on Out-of-Sample Performance
• Estimating and backtesting risk under heavy tails
• Estimating and backtesting risk under heavy tails