Pseudo-Mathematics and Financial Charlatanism¶
Bailey, D. H., Borwein, J. M., López de Prado, M., & Zhu, Q. J. (2014). Pseudo-Mathematics and Financial Charlatanism: The Effects of Backtest Overfitting on Out-of-Sample Performance. Notices of the American Mathematical Society, 61(5), 458-471.
Cited by¶
3 citations across 3 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Data Leakage
- In finance, a strategy backtested with look-ahead bias — restated earnings, survivorship-filtered universes, future fundamentals — looks profitable in backtest and disappoints live.
This sourceShows how look-ahead bias and backtest overfitting inflate in-sample returns that collapse live, the finance analogue of temporal target leakage.
Supported in partVerified against the work's full text
The paper shows overfit backtests look profitable and disappoint out-of-sample, but attributes this to overfitting, not to look-ahead bias, restated earnings or survivorship-filtered universes.
“When financial advisors do not control for overfitting, positive backtested performance will often be followed by negative”
- In finance, a strategy backtested with look-ahead bias — restated earnings, survivorship-filtered universes, future fundamentals — looks profitable in backtest and disappoints live.
- Proxy–Target Fidelity
- In finance, a credit rating proxies for default probability and a backtest proxies for live strategy performance.
This sourceShows a strategy's backtest (in-sample) performance is a poor proxy for live (out-of-sample) performance, easily inflated by overfitting — the proxy-target fidelity failure between a backtest and live trading.
Supported in partVerified against the work's full text
Supports the backtest half (in-sample backtest results are an inflated, unreliable stand-in for out-of-sample performance); says nothing about credit ratings as a proxy for default probability.
“positive backtested performance will often be followed by negative”
- In finance, a credit rating proxies for default probability and a backtest proxies for live strategy performance.
- Researcher Degrees of Freedom
- In financial backtesting, strategy researchers explore hundreds of variants on the same historical data and report the best, the pattern known there as backtest overfitting.
This sourceFormalizes backtest overfitting and the deflated Sharpe ratio correcting for the number of trials.
SupportedVerified against the work's full text
Bailey et al. describe researchers backtesting an enormous number of configurations on historical data, presenting the winner and hiding hundreds of trials, and name this backtest overfitting.
“The problem is, AIC’s assessment did not take into account the hundreds of other trials that the researcher neglected to mention.”
- In financial backtesting, strategy researchers explore hundreds of variants on the same historical data and report the best, the pattern known there as backtest overfitting.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 3 of 3 citations: 1 supported, 2 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Links previously used in the corpus¶
Before the registry existed this work was also linked 1 other way.
Registry ID ref:93d64b7def30 · see in the full table