Pseudo-Mathematics and Financial Charlatanism: The Effects of Backtest Overfitting on Out-of-Sample Performance
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index; none of the 6 sources its claims cite is checked for support yet.
Abstract
Another thing I must point out is that you cannot prove a vague theory wrong.[…] Also, if the process of computing the consequences is indefinite, then with a little skill any experimental result can be made to look like the expected consequences.
Overview
CoChat Summary
TL;DR
The paper argues that backtest overfitting makes it easy to manufacture high in-sample Sharpe ratios, while out-of-sample performance can be zero or negative, especially when performance series have memory. It derives a Minimum Backtest Length and uses simulations plus a seasonal-strategy example to show that high in-sample Sharpe ratios can arise from skill-less random data.
Key findings
- With only \(N=10\) independent strategy configurations, the expected maximum in-sample Sharpe ratio is 1.57 even though all strategies have expected out-of-sample Sharpe ratio of zero; with \(N=128\) trials, the expected maximum Sharpe ratio is above 2.6.
- If only five years of data are available, no more than 45 independent model configurations should be tried to keep the expected maximum in-sample Sharpe ratio at 1 while expected out-of-sample Sharpe ratio is 0; after only seven independent configurations, the expected maximum in-sample Sharpe ratio is 1 for a two-year backtest, with expected out-of-sample Sharpe ratio 0.
- Adding a global constraint or serial dependence creates compensation effects: recentering makes out-of-sample performance negative even for a trendless process, with the p-value for the IS-performance relation equal to 0; for an AR(1) process with \(\phi=0.995\), the half-life is about 138 observations and the p-value for the IS-performance relation is again 0.
- In a synthetic seasonal-strategy example using 1,000 daily prices and 8,800 parameter combinations, the optimal rule has an annualized Sharpe ratio of 1.27 and a PSR-Stat of 2.83, implying less than 1 percent probability that the true Sharpe ratio is below 0, despite no true seasonal effect.
Methods
- Theoretical derivation: assumes IID Normal excess returns and uses the Sharpe ratio, extreme-value/Gumbel approximations, and propositions to derive the expected maximum Sharpe ratio and Minimum Backtest Length (MinBTL).
- Monte Carlo simulations: generates Gaussian random walks of size \(T=1000\), splits them into 500 in-sample and 500 out-of-sample observations, and studies selection of the best in-sample Sharpe ratio; also runs recentered and first-order autoregressive (\(\phi=0.995\)) variants.
- Practical application: performs a grid search over Entry day (1–22), Holding period (1–20), Stop loss (0–10), and Side (\(\pm1\)), forming 8,800 parameter combinations on a 1,000-day random-walk price series, and reports the optimal Sharpe ratio and PSR-Stat.
Limitations
- The paper states that MinBTL is a necessary but not sufficient condition to avoid overfitting, and that Proposition 1 assumes independent trials, which is a conservative estimate; if trials are not independent, the number of independent trials could be derived using a dimension-reduction procedure such as Principal Component Analysis.
- The paper states that the hold-out method cannot assess the representativeness of a backtest because it does not account for the number of trials attempted, and it leaves a more precise measure of backtest overfitting to Bailey et al. [1].
- Evident from the text: the simulations and practical example rely on synthetic IID Normal/Gaussian random walks and specific parameter choices rather than real market data, so the numerical illustrations are model-based demonstrations rather than empirical estimates.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
0 Valid · 8 Not valid · 6 Not checked · 68 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Figure 6 shows that adding a single global constraint causes the OOS performance to be negative even though the underlying process was trendless.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This illustrates the fact that, in absence of compensation effects, overfitting the IS performance ( x -axis) has no bearing on the OOS performance ( y -axis), which remains around zero.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Proposition 1. Given a sample of IID random variables, xn Z , n 1 ; : : : ; N , where Z is the CDF of the Standard Normal distribution, the expected maximum of that sample, E max N E max φ xn γ , can be approximated for a large N as”
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
- Rests on 3 assumptions not shown here.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Theorem 2. The Minimum Backtest Length (MinBTL, in years) needed to avoid selecting a strategy with an IS Sharpe ratio of E max N among N independent strategies with an expected OOS Sharpe ratio of zero is (6)”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 3 assumptions not shown here.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This has allowed us to determine the Minimum Backtest Length (MinBTL) needed to avoid selecting a strategy with a given IS Sharpe ratio among N trials with an expected OOS Sharpe ratio of zero.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
45 more claims
Create a free account to see all 82 claims and every source verdict.
- It may state two separate claims as one. 21
- Probably not a substantial claim. 16
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“For example, we could explore all nodes that span the set φ 1 ; : : : ; 22 γ for Entry day , the set φ 1 ; : : : ; 20 γ for Holding period , the set φ 0 ; : : : ; 10 γ for Stop loss , and φ 1 ; 1 γ for Side . The parameter combinations involved form a four-dimensional mesh of 8,800 elements.”
Reported 8800 · recomputed 9680
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Is Backtest Overfitting a Fraud? · p. 9
“Consider an investment manager who emails his stock market forecast for the next month to 2 n x prospective investors, where x and n are positive integers.”
§ Is Backtest Overfitting a Fraud? · p. 9
“The investment manager is hiding the fact that for every one of the x successful witnesses, he has tried 2 n unsuccessful ones”
Citations
Cites
Why Most Published Research Findings Are False
Ioannidis, J. P. A. (2005) · CHANCE · doi:10.1080/09332480.2005.10722754 · Cited by 4,702
Embrechts, P., Klüppelberg, C., & Mikosch, T. (1997) · doi:10.1007/978-3-642-33483-2 · Cited by 4,402
Extreme Values, Regular Variation and Point Processes
Resnick, S. I. (1987) · Springer Series in Operations Research and Financial Engineering · doi:10.1007/978-0-387-75953-1 · Cited by 3,158
Hawkins, D. M. (2004) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci0342472 · Cited by 2,522
Feynman, R. (2017) · The MIT Press eBooks · doi:10.7551/mitpress/11068.001.0001 · Cited by 1,881
A Reality Check for Data Snooping
White, H. (2000) · Econometrica · doi:10.1111/1468-0262.00152 · Cited by 1,851 · cited 1×
“—Richard Feynman [1964]”
Rules for Ordering Uncertain Prospects
Hadar, J., & Russell, W. R. (1969) · American Economic Review · Cited by 1,720
Stepwise Multiple Testing as Formalized Data Snooping
Romano, J. P., & Wolf, M. (2005) · Econometrica · doi:10.1111/j.1468-0262.2005.00615.x · Cited by 1,019
Weiss, S. M., & Kulikowski, C. A. (1991) · Morgan Kaufmann Publishers Inc. eBooks · Cited by 898
The Statistics of Sharpe Ratios
Lo, A. W. (2002) · Financial Analysts Journal · doi:10.2469/faj.v58.n4.2453 · Cited by 843
Research works printed but not linked: 4
- [3][3] , Drawdown-based stop-outs and the triple penance rule, 2013, working paper. Available at http://ssrn.com/abstract=2201302 . -
- [9][9] C. Harvey and Y. Liu , Backtesting, working paper, SSRN, 2013, http://ssrn.com/abstract=2345489 . -
- [10][10] C. Harvey, Y. Liu , and H. Zhu , : : : and the crosssection of expected returns, working paper, SSRN, 2013, http://ssrn.com/abstract=2249314 . -
- [12][12] Y. Hirsch , Don't Sell Stocks on Monday , Penguin Books, 1st edition, 1987. -
Cited by
Items 101–200 of 208
The ABC’s of the alternative risk premium: academic roots
Gorman, S. A., & Fabozzi, F. J. (2021) · Journal of Asset Management · doi:10.1057/s41260-021-00234-0 · Cited by 3
Minimizing Basel III Capital Requirements with Unconditional Coverage Constraint
Kleinknecht, M., & Ng, W. L. (2015) · Intelligent systems in accounting, finance and management/Intelligent systems in accounting, finance & management · doi:10.1002/isaf.1370 · Cited by 2
Pattern searcher for decision making of trading agents using Genetic Algorithm
Cacique, F. V., & Pereira, A. C. M. (2020) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec48606.2020.9185704 · Cited by 2
“Several steps can help to reduce the overfitting presence, including developing models for entire asset classes, rather than for specific securities [16], and reducing the model complexity [17].”
BackgroundRecent Trends in Empirical Finance
de Prado, M. L. (2015) · The Journal of Portfolio Management · doi:10.3905/jpm.2015.42.1.029 · Cited by 2
Self-citationA Framework for Assessing Factors and Implementing Smart Beta Strategies
Hsu, J. C., Kalesnik, V. M., & Viswanathan, V. (2015) · The Journal of Index Investing · doi:10.3905/jii.2015.2015.1.035 · Cited by 2
Limitations of Quantitative Claims About Trading Strategy EvaluationPreprint
Harris, M. (2016) · SSRN Electronic Journal · doi:10.2139/ssrn.2810170 · Cited by 2
A Practical Solution to the Multiple-Testing Crisis in Financial ResearchPreprint
de Prado, M. L. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3177057 · Cited by 2
Self-citationWhat Is Quality?Preprint
Hsu, J. C., Kalesnik, V. M., & Kose, E. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.2971185 · Cited by 3
Learning the dynamics of technical trading strategiesPreprint
Murphy, N., & Gebbie, T. (n.d.) · RePEc: Research Papers in Economics · Cited by 3
International High-Frequency Arbitrage for Cross-Listed StocksPreprint
Dionne, G., Poutré, C., & Yergeau, G. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4066962 · Cited by 2
Asset ManagementPreprint
Vanini, P. (2016) · SSRN Electronic Journal · doi:10.2139/ssrn.2710123 · Cited by 2
False Findings in Finance: The Hidden Costs of Misleading Results in the Age of AIPreprint
Bloch, D. A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5345109 · Cited by 2
Pallotta, A., & Ciciretti, V. (2025) · Finance research letters · doi:10.1016/j.frl.2025.107997 · Cited by 1
Choi, I. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01382-0 · Cited by 2
Moroke, N. D. (2026) · Mathematical and Computational Applications · doi:10.3390/mca31040133 · Cited by 1
“All pairwise transfer-entropy estimates (TE j → i ( ℓ ∗ ) ) used in the metabolic saliency formula (Definition 10) are computed exclusively on the training baseline period (January 2015 to December 2018, ≈ 992 days) to prevent look-ahead bias [56].”
Hao, Z., Chen, H., & Qi, R. (2026) · Algorithms · doi:10.3390/a19080704 · Cited by 2
“The design problem is max g w ( g ) subject to κ ( g ) ∈ [ κ min , κ max ] over a designated evaluation period, (3) with an operational band [ κ min , κ max ] = [ 10, 12 ] trades/day in this paper and the economic requirement w > w ∗ .”
A Bayesian Approach to Backtest Overfitting
Witzany, J. (2017) · Risks · doi:10.3390/risks9010018 · Cited by 6
“(Bailey et al. 2014) Bailey, David H., Jonathan Borwein, Marcos Lopez de Prado, and Qiji Jim Zhu.”
BackgroundMethodInfluentialPortfolio Optimization Efficiency Test Considering Data Snooping Bias
Kresta, A., & Wang, A.-L. (2020) · Business Systems Research Journal · doi:10.2478/bsrj-2020-0016 · Cited by 2
“These estimates can be directly applied in the portfolio optimization model (4)-(6).”
BackgroundStatistical Overfitting and Backtest Performance
Bailey, D. H., Ger, S., de Prado, M. L., et al. (2015) · Elsevier eBooks · doi:10.1016/b978-1-78548-008-9.50020-4 · Cited by 1
Self-citationde Prado, M. L., & Rebonato, R. (2016) · The Journal of Investing · doi:10.3905/joi.2016.25.3.142 · Cited by 1
Self-citationA Comparative Study of Deep Learning Techniques for Financial Indices Prediction
Ketsetsis, A. P., Giannoutakis, K. M., Spanos, G., Samaras, N., Hristu‐Varsakelis, D., Thomas, D., & Tzovaras, D. K. (2021) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-79150-6_24 · Cited by 1
“Moreover, a trading strategy was implemented, the Moving Crossing Average (Golden Cross) [2], in order to test the predictive ability of the selected methods in real-world trading scenarios.”
How Skewed are Simultaneously Long-Short Trading Gains?
Baumann, M. H. (2023) · European Control Conference (ECC) · doi:10.23919/ecc57647.2023.10178415 · Cited by 1
The Poverty of Academic Finance Research: Spread Trading Strategies in the Crude Oil Futures MarketPreprint
Donninger, C. (2015) · SSRN Electronic Journal · doi:10.2139/ssrn.2617585 · Cited by 1
Know Your System! – Turning Data Mining from Bias to Benefit Through System Parameter PermutationPreprint
Walton, D. (2014) · SSRN Electronic Journal · doi:10.2139/ssrn.2423187 · Cited by 1
de Prado, M. L. (2015) · SSRN Electronic Journal · doi:10.2139/ssrn.2599105 · Cited by 1
Self-citationThe Mixed vs the Integrated Approach to Style Investing: Much Ado About Nothing?Preprint
Leippold, M., & RRegg, R. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.2887117 · Cited by 1
Systematic Hedge Fund Risk Management: An OverviewPreprint
Mazaheri, M. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3431610 · Cited by 1
Epistemic Limits of Empirical Finance: Causal Reductionism and Self-ReferencePreprint
Polakow, D. A., Gebbie, T., & Flint, E. J. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4646664 · Cited by 4
The Case for Causal Factor InvestingPreprint
de Prado, M. L., Lipton, A., & Zoonekynd, V. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4774522 · Cited by 1
Self-citationHow to Use the Sharpe RatioPreprint
de Prado, M. L., Lipton, A., & Zoonekynd, V. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5520741 · Cited by 3
Self-citationReinforcement Learning in Finance: From Current Practice to Standards and FrameworksPreprint
Jander, M., van Heeswijk, W., & Mes, M. R. K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5703882 · Cited by 1
The False Discovery Rate in Finance: Identification Failure and Search-Adjusted EstimationPreprint
de Prado, M. L., & Fabozzi, F. J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6450418 · Cited by 1
Self-citationDeflating the Sharpe RatioPreprint
de Prado, M. L. (2014) · SSRN Electronic Journal · doi:10.2139/ssrn.2465675
Self-citationSimulation as a Stock Market Backtesting ToolPreprint
Cooper, T. (2014) · SSRN Electronic Journal · doi:10.2139/ssrn.2425436
Dubois, R. (2014) · SSRN Electronic Journal · doi:10.2139/ssrn.2474184
Correctness of backtest engines
Low, R., Paape, S. M., & Platen, A. (2017) · The Journal of Investment Strategies · doi:10.21314/jois.2017.085
“Here one often speaks of backtest overfitting, see [1, 2, 3] and also [9, Chapter 6] for a detailed discussion.”
BackgroundKleinknecht, M., & Ng, W. L. (2016) · SSRN Electronic Journal · doi:10.2139/ssrn.2717051
Sentiment and the Performance of Technical IndicatorsPreprint
Feng, S., Zychowicz, E. J., & Zychowicz, E. J. (2012) · SSRN Electronic Journal · doi:10.2139/ssrn.2140230
The Structure of a Machine-Built Global MacroForecasting System
Chen, J., & Tindall, M. L. (2016) · The Journal of Alternative Investments · doi:10.3905/jai.2016.19.1.093
New nancial analysis tools at CARMA
Salehipour, A. (2015)
Calibration of Bubble Indicators for Foreign Exchange Markets
Carron, K. T. (2015)
Kashyap, R. (2015) · SSRN Electronic Journal · doi:10.2139/ssrn.2661949
Using Maharishi Vedic Science to Understand the Share MarketPreprint
Price, J. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3090305
How Hard Is It to Pick the Right Model?Preprint
Aparicio, D., & de Prado, M. L. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3044740
Self-citationDid Academic Finance Play a Role in the Global Financial Crisis?
Rutledge, A. (2018) · The journal of structured finance · doi:10.3905/jsf.2018.24.2.007
Better predictability of arbitrage strategies trained among less attentionstocks
Fang, J., & Lin, J. (2019) · IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) · doi:10.1109/icphys.2019.8780281
Matching Market Views and Strategies: A New Risk Framework for Optimal SelectionPreprint
Reghai, A., & Riboulet, G. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3122015
Forecast Optimization via Parameter Tuning: Performance Gain and Overfit
Soloveychik, I. (2020) · The Journal of Financial Data Science · doi:10.3905/jfds.2020.1.044
Is it a great Autonomous FX Trading Strategy or you are just fooling yourselfPreprint
Bernardini, M. S., & de Castro, P. A. L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.07217
“Overfitting in finance leads to unrealistic expectation about the performance and therefore it can be used to mislead investors to bet in overfitted autonomous trading systems, which could be built by naive or even malicious developers [27].”
BackgroundMethodInfluentialCoyne, A. E. (2020) · Open University of Cape Town (University of Cape Town)
mt5b3: A Framework for Building AutonomousTraders.Preprint
de Castro, P. A. L. (2021) · arXiv (Cornell University)
TimeGym: Debugging for Time Series Modeling in PythonPreprint
Seca, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.01404
“Because we have an infinite amount of time series to sample from, the Bonferroni correction is not required, unlike in real-world datasets in which overfitting is a frequent problem [2].”
BackgroundAn Alternative Application for Detecting Statistical Significance in Investment StrategiesPreprint
Alpay, A., & Goodwin, K. R. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3281809
International High-Frequency Arbitrage for Cross-Listed StocksPreprint
Poutré, C., Dionne, G., & Yergeau, G. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3890433
The Missing Label Problem: Addressing False Assumptions Improves Ligand-Based Virtual ScreeningPreprint
Martin, L. J., & Bowen, M. T. (2019) · ChemRxiv · doi:10.26434/chemrxiv.9758423.v1
Brasell, S. (2019) · doi:10.26686/wgtn.17151590
Brasell, S. (2019) · doi:10.26686/wgtn.17151590.v2
The Shape of Performance Curve in Financial Time SeriesPreprint
Alonso, M. N. I., & Srivastava, S. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3986154
Naqvi, A. (2021) · doi:10.1002/9781119601838.ch6
Paolella, M. S. (2018) · Wiley series in probability and statistics · doi:10.1002/9781119432036.biblio
The Missing Label Problem: Addressing False Assumptions Improves Ligand-Based Virtual ScreeningPreprint
Martin, L. J., & Bowen, M. T. (2019) · ChemRxiv · doi:10.26434/chemrxiv.9758423
(2017) · Elsevier eBooks · doi:10.1016/b978-1-78548-162-8.50014-1
BacktestingPreprint
de Prado, M. L. (2015) · SSRN Electronic Journal · doi:10.2139/ssrn.2606462
Self-citationBailey, D. H., & Zhu, Q. J. (2020) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-030-36568-4_15
Self-citationTulchinsky, I. (2015) · doi:10.1002/9781119057871.refs
Tansil, T. M., Rusli, L. P., & Budiarto, E. (2022) · International Conference on Engineering and Information Technology for Sustainable Industry (ICONETSI) · doi:10.1145/3557738.3557943
“[18] Two options trading strategies that are selected to be evaluated are credit spread strategy and debit spread strategy.”
BackgroundOptimal Trend Following Rules in Two-State Regime-Switching ModelsPreprint
Zakamulin, V., & Giner, J. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4217513
A Model-Based Approach Machine Learning to Scalable Portfolio Selection
Gularte, A. P. D. S., & Curtis, V. (2023) · International Journal on Cybernetics & Informatics · doi:10.5121/ijci.2023.120303
“In the numerical example of [33], the performance of the out-of-sample portfolio is evaluated through Monte Carlo simulation, improving the Sharpe by about 31.3% (for a broader discussion of in-sample vs. out-of-sample performance, see [39].”
MethodInfluentialOverfitting in Portfolio OptimizationPreprint
Maggiolo, M., & Szehr, O. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4483959
Predicting Price Trends Combining Kinetic Energy and Deep Reinforcement LearningPreprint
Zahedi, M., & Ghotbi, M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4502473
Maier‐Paape, S., Júdice, P., Platen, A., & Zhu, Q. J. (2023) · CMS/CAIMS books in mathematics · doi:10.1007/978-3-031-33321-7_1
Self-citationHasnain, S. I., Mohanty, S., Acharya, K. K., et al. (2023) · Asian Journal of Management and Commerce · doi:10.22271/27084515.2023.v4.i2c.210
“Accuracy: This ability of back testing in algo trading enables the trader to run the algorithms on historical data, which further helps in removing any mistake of a trading system before executing it live (Bailey, Borwein, Lopez and Zhu, 2014) [17] .”
The Three Types of BacktestsPreprint
Joubert, J. F., Sestovic, D., Barziy, I., Distaso, W., & de Prado, M. L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4897573
Self-citationMontes-Gómez, L. F., Aguilar, D. S. G., & Pinzon-Sanchez, L. A. (2024) · DYNA · doi:10.15446/dyna.v91n233.112700
“…such as channel breaks, moving averages, supports and resistances, trading volume, chose measurement parameters for each, the objective was to establish as many rules as possible and determine which was the most profitable over a 100-year time span (1897-1996), and used the Dow Jones index [19].”
BackgroundMethodLimitations of News Sentiment Analysis in Short-term Stock Return Prediction: A Multi-Level ApproachPreprint
Kengmegni, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5086825
A Two-Layer Ensemble Architecture for Enhanced Directional Price Prediction in Financial MarketsPreprint
Hassanizorgabad, S., & Yumuşak, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5156285
AGNOSTIC — Effective Quantitative Finance With Online LearningPreprint
Bochud, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5242085
A Protocol for Causal Factor InvestingPreprint
de Prado, M. L., & Zoonekynd, V. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5277078 · Cited by 2
Self-citationThe Three-agent Framework: A Case Study to Improve AI Compliance for Hedge FundsPreprint
Bychkov, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5373676
van Thanh, N., & Hau, N. T. (2025) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse68178.2025.11309453
“While powerful, these methods often decouple the investment pipeline—splitting alpha generation, model learning, and allocation into isolated steps—limiting their adaptability and overall performance [1].”
Han, D., & Kim, Y. (2026) · Systems · doi:10.3390/systems14010111 · Cited by 1
hpFX: A Parallel Orchestration Framework for Indicator-Based Forex Simulations
Belgin, M. (2026) · Computational Economics · doi:10.1007/s10614-025-11261-z
The Sharpe Stability Ratio: Temporal Consistency of Risk-Adjusted PerformancePreprint
Traver, M. B., & Domínguez, A. R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6344658
Fischer, K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6388459
Gatto, D. V. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6636018 · Cited by 1
Lazar, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6739222
Rauf, K., & Sutopo, J. (2026) · Cureus Journal of Computer Science. · doi:10.7759/s44389-026-00083-1 · Cited by 1
Angel Priya, J., Barot, O., Venkatesh, S., Kumar, R., Padmapriya, R., & Pimplapure, V. (2026) · 2026 6th International Conference on Recent Trends in Computer Science and Technology (ICRTCST) · doi:10.1109/icrtcst68392.2026.11545351
RetractedBoscariol, R. (2026) · Qeios · doi:10.32388/3tfsk1
LEAP: A Leakage-Free Evolutionary Alpha Pipeline for NLP-Driven DJIA Prediction
Cunha, M. P., Dalmazo, B. L., de Mattos, V. L. D., Pinto, R. F., Bruno, D. R., Borges, E. N., Lucca, G., Cardoso, F. C., & Berri, R. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30494-0_5
Dijital Varlıklar ve Yapay Zekâ Çağında Yatırım Analizi Yeni Nesil Portföy Yönetimi Stratejileri
Sarı, B. (2026) · Akademisyen Kitabevi eBooks · doi:10.37609/akya.4273
Correct-by-Construction Factor Computation: A Verifiably Point-in-Time Engine for Tradeable SignalsPreprint
Wu, K. T., & Wu, K. T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7016199
Sean, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6829578
Saif, Z. U., Gillani, S., & Toor, A. G. (2026) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/1918
Sapazhkou, R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7235818
Optimized Artificial Neural Networks for Improved Gastrointestinal Anomaly Classification
Verma, C., Rajan, N. P., Sakthivel, N., Kumar, A., Deshpande, S., & Shrimali, M. (2026) · 2026 2nd International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI) · doi:10.1109/icscai68849.2026.11649202
Zhang, B., Chang, Z., Zhang, Y., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7356724
Predicting Bullish Reversals with LightGBM: A Systematic Trading Strategy for Brazilian Equities
Alves, W., & Callou, G. R. D. A. (2026) · doi:10.5753/semish.2026.23803
“To better reflect real, world conditions, a transaction cost proportional to the traded volume is considered, typically around 0.1% in the Brazilian market, applied to both entry and exit, as recommended in the literature [Bailey et al. 2014].”
InfluentialKaratyhin, T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7417918
Metadata
- Authors
- Bailey, D. H., Borwein, J. M., López de Prado, M., & Zhu, Q. J.
- Affiliations
- Lawrence Berkeley National Laboratory (US)
- Western Michigan University (US)
- Venue
- Notices of the American Mathematical Society
- Publisher
- American Mathematical Society (AMS)
- Published
- 2014-05-01
- Volume
- 61
- Issue
- 5
- Pages
- 458
- ISSN
- 0002-9920 (ISSN-L)
- 1088-9477
- OpenAlex
- W3125595766
- Cited by
- 221
- References
- 25
- Citations by year
- 2026: 43 · 2025: 18 · 2024: 12 · 2023: 16 · 2022: 6 · 2021: 23 · 2020: 15 · 2019: 16 · 2018: 16 · 2017: 11 · 2016: 15 · 2015: 20 · 2014: 9
- FWCI
- 33.55
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Notices of the American Mathematical Society (publishedVersion)
- NOVA (University of Newcastle Australia) (submittedVersion)
- Funders
- American Mathematical Society
- University of Oxford
- Eidgenössische Technische Hochschule Zürich
- University of California, Irvine
- Lawrence Berkeley National Laboratory
- Topics
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Economics, Econometrics and Finance › Finance › Stochastic processes and financial applications
- Keywords
- backtest overfitting, out-of-sample performance, financial forecasting, model selection, time series forecasting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.