pith. sign in

arxiv: 2604.09060 · v2 · pith:KKPZPJQZnew · submitted 2026-04-10 · 💻 cs.CE · cs.IR

Taming the Black Swan: A Momentum-Gated Hierarchical Optimisation Framework for Asymmetric Alpha Generation

Arya Chakraborty , Randhir Singh This is my paper

Pith reviewed 2026-05-21 01:44 UTC · model grok-4.3

classification 💻 cs.CE cs.IR
keywords momentum strategiesportfolio optimizationalpha generationSortino ratiomarket regime adaptationvolatility-adjusted filtersblack swan eventshierarchical optimization
0
0 comments X

The pith

The AEGIS framework engineers synthetic beta to capture high-growth equity returns with defensive stability.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper introduces the Adaptive Equity Generation and Immunisation System (AEGIS) to address the winner's curse in conventional momentum strategies. The framework uses a volatility-adjusted momentum filter to gauge trend strength and a minimax correlation algorithm to ensure diversification. It then applies sequential least squares programming to allocate capital optimizing the Sortino ratio. This setup lets the portfolio adjust to different market conditions, dampening crashes in bad times and keeping strong gains in good times. The 20-year backtest indicates it can deliver better risk-adjusted performance than standard benchmarks.

Core claim

The paper claims that the AEGIS framework fundamentally reengineers the growth-stability trade-off in momentum investing. By leveraging volatility-adjusted momentum to identify trends, minimax correlation to enforce diversification, and SLSQP to optimize for the Sortino ratio, the model dynamically adapts to market regimes. It lowers crash intensity in bear markets by decoupling risks and retains upside in bull markets. The 20-year walk-forward backtest from 2006-2025 shows substantial excess alpha versus the S&P 500 while matching NASDAQ-100 capital appreciation with reduced downside volatility and improved resilience.

What carries the argument

The Adaptive Equity Generation and Immunisation System (AEGIS) that integrates volatility-adjusted momentum filtering, minimax correlation diversification, and SLSQP optimization for the Sortino ratio.

If this is right

  • The portfolio dynamically adapts to distinct market regimes.
  • Crash intensity is reduced in bear markets through decoupling of correlated risks.
  • Asymmetric upside participation is maintained during bull runs.
  • Substantial excess alpha is produced relative to the S&P 500 benchmark.
  • Capital appreciation matches the NASDAQ-100 with lower downside volatility.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This regularization approach could be extended to optimize other performance metrics beyond the Sortino ratio.
  • Similar techniques might help in constructing resilient portfolios in non-equity asset classes.
  • The results imply that synthetic beta engineering is feasible for balancing concentration and diversification.
  • Testing the framework in real-time trading environments would provide further validation of its regime-adaptation capabilities.

Load-bearing premise

The 20-year walk-forward backtest covering 2006-2025 sufficiently demonstrates the framework's ability to dynamically adapt to market regimes without overfitting or data snooping biases.

What would settle it

A significant underperformance in a subsequent out-of-sample period or a new financial crisis where drawdowns exceed those of the S&P 500 would falsify the claim of improved structural resilience.

Figures

Figures reproduced from arXiv: 2604.09060 by Arya Chakraborty, Randhir Singh.

Figure 1
Figure 1. Figure 1: Automated Data Acquisition Architecture. The pipeline scrapes constituent tickers from Wikipedia, executes asynchronous requests to the Yahoo [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The AEGIS Walk-Forward Validation Architecture. The system operates via a nested-loop protocol: the outer annual cycle executes the Adaptive [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The Signal Generation Module. This module executes a hierarchical selection protocol. First, the system ingests raw price data and identifies the [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: The Immunisation Layer. This module constructs the portfolio iteratively to ensure robust diversification. First, the Momentum Gate filters the candidate [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: The Allocation Engine. This module executes the final capital distribution. The Anchor Triad and selected Diversifiers are merged into a single Full [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Graph 1 and 2: 20-Year Capital Appreciation: AEGIS Broad Market Dominance (S&P 500) and Tech-Parity (NASDAQ) Trajectory ($10,000 Initial [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Graph 3 and 4: 20-Year Capital Appreciation: AEGIS vs. Dow Jones, S&P 400 MidCap, and S&P 600 SmallCap Indices. This represents Terminal [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Graph 6 and 7: Year-wise annual volatility and max drawdown of AEGIS framework during the 20-year walk-forward backtest with the marked [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Graph 8: Comparative Underwater Drawdown Analysis (2006-2025). The plot tracks the percentage decline from historical high-water marks, illustrating [PITH_FULL_IMAGE:figures/full_fig_p013_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Graph 11 and 12: The Return vs. Volatility scatter plot of AEGIS framework demonstrating the High Returns and Low Returns nature of the system [PITH_FULL_IMAGE:figures/full_fig_p014_10.png] view at source ↗
read the original abstract

Conventional momentum strategies, despite their proven efficacy in generating alpha, frequently suffer from the "Winner's Curse", a structural vulnerability in which high performing assets exhibit clustered volatility and severe drawdowns during market reversals. To counteract this propensity for momentum crashes, this study presents the Adaptive Equity Generation and Immunisation System (AEGIS), a novel framework that fundamentally reengineers the trade-off between growth and stability. By leveraging a volatility-adjusted momentum filter to identify trend strength and employing a minimax correlation algorithm to enforce structural diversification, the model utilises sequential least squares programming (SLSQP) to optimise capital allocation for the sortino ratio. This architecture allows the portfolio to dynamically adapt to distinct market regimes: explicitly lowering the intensity of crashes during bear markets by decoupling correlated risks, while retaining asymmetric upside participation during bull runs. Empirical validation via a comprehensive 20-year walk-forward backtest (2006-2025), which covers significant stress events like the 2008 Global Financial Crisis, confirms that the framework produces substantial excess alpha relative to the standard S&P 500 benchmark. Notably, the strategy successfully matched the capital appreciation of the high-beta NASDAQ-100 index while achieving significantly reduced downside volatility and improved structural resilience. These results suggest that synthetic beta can be effectively engineered through mathematical regularisation, enabling investors to capture the high-growth characteristics of concentrated portfolios while preserving the defensive stability typically associated with broad-market diversification.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper proposes the Adaptive Equity Generation and Immunisation System (AEGIS), a momentum-gated hierarchical optimisation framework. It combines a volatility-adjusted momentum filter for trend identification, a minimax correlation algorithm to enforce diversification, and SLSQP optimisation of the Sortino ratio for capital allocation. The central claim is that a 20-year walk-forward backtest (2006-2025) covering events such as the 2008 GFC demonstrates substantial excess alpha over the S&P 500 benchmark, with the strategy matching NASDAQ-100 capital appreciation while delivering significantly lower downside volatility and greater structural resilience.

Significance. If the reported performance holds after addressing verification gaps and potential biases, the framework would offer a concrete method for engineering asymmetric returns that combine concentrated-portfolio upside with broad-market downside protection. This directly targets the known 'winner's curse' and momentum-crash vulnerabilities in conventional momentum strategies through explicit regularisation steps, which could be of practical interest to quantitative portfolio managers.

major comments (2)
  1. [Abstract] Abstract: the claims of 'substantial excess alpha' and 'significantly reduced downside volatility' while matching NASDAQ-100 appreciation are unsupported by any numerical results (e.g., cumulative returns, volatility, maximum drawdown, or statistical significance tests). This absence is load-bearing because the entire empirical validation rests on these unquantified assertions.
  2. [Empirical validation] Empirical validation paragraph: capital allocation is optimised via SLSQP for the Sortino ratio on the same historical data used in the 20-year walk-forward backtest. Without explicit confirmation that momentum thresholds, correlation minimax parameters, and rebalancing windows were fixed a priori rather than tuned after inspecting full-period outcomes, the reported regime-adaptive resilience cannot be distinguished from in-sample fitting.
minor comments (2)
  1. The abstract introduces 'synthetic beta' and 'mathematical regularisation' without defining these terms or contrasting them with standard mean-variance or risk-parity methods.
  2. The backtest description omits the asset universe, rebalancing frequency, and transaction-cost assumptions, all of which are required for reproducible evaluation of the claimed resilience.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed comments on our manuscript. We have reviewed the points raised regarding the abstract and the empirical validation section. Below we respond to each major comment in turn, indicating where revisions will be made to strengthen the paper.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claims of 'substantial excess alpha' and 'significantly reduced downside volatility' while matching NASDAQ-100 appreciation are unsupported by any numerical results (e.g., cumulative returns, volatility, maximum drawdown, or statistical significance tests). This absence is load-bearing because the entire empirical validation rests on these unquantified assertions.

    Authors: We agree that the abstract would be strengthened by including concrete numerical support for the performance claims. In the revised version we will add specific metrics drawn from the 20-year walk-forward backtest, including cumulative returns, annualized volatility, maximum drawdown, and any statistical significance measures relative to the S&P 500 and NASDAQ-100 benchmarks. This will make the assertions directly verifiable while remaining within abstract length constraints. revision: yes

  2. Referee: [Empirical validation] Empirical validation paragraph: capital allocation is optimised via SLSQP for the Sortino ratio on the same historical data used in the 20-year walk-forward backtest. Without explicit confirmation that momentum thresholds, correlation minimax parameters, and rebalancing windows were fixed a priori rather than tuned after inspecting full-period outcomes, the reported regime-adaptive resilience cannot be distinguished from in-sample fitting.

    Authors: The concern about potential in-sample bias in parameter selection is well taken. The walk-forward design used parameters determined exclusively from preceding training windows and applied forward without subsequent adjustment on the full test period. To remove any ambiguity we will insert an explicit subsection detailing the a-priori fixing process for momentum thresholds, minimax correlation parameters, and rebalancing windows, including the exact training-window rules employed. revision: yes

Circularity Check

1 steps flagged

SLSQP Sortino optimization on backtest data renders reported alpha and resilience fitted by construction

specific steps
  1. fitted input called prediction [Abstract / Empirical validation paragraph]
    "the model utilises sequential least squares programming (SLSQP) to optimise capital allocation for the sortino ratio. ... Empirical validation via a comprehensive 20-year walk-forward backtest (2006-2025) ... confirms that the framework produces substantial excess alpha relative to the standard S&P 500 benchmark. Notably, the strategy successfully matched the capital appreciation of the high-beta NASDAQ-100 index while achieving significantly reduced downside volatility"

    SLSQP selects weights to maximize Sortino on the identical 2006-2025 period whose realized returns, volatility, and drawdowns are then cited as evidence of alpha and resilience. The reported outperformance is therefore the direct numerical output of the in-sample optimization rather than a prediction independent of the fit.

full rationale

The framework's core performance claims rest on a 20-year walk-forward backtest in which capital weights are chosen by SLSQP to maximize the Sortino ratio on the very data whose outcomes are then reported. This matches the 'fitted input called prediction' pattern: the optimization step directly produces the metrics (excess alpha, NASDAQ-matched upside with lower downside) that are presented as validation. No independent out-of-sample test or fixed a-priori parameters are shown to break the dependence. The walk-forward label does not remove the circularity when the objective itself is fitted to the evaluation window.

Axiom & Free-Parameter Ledger

2 free parameters · 2 axioms · 1 invented entities

The abstract provides limited detail on exact parameters and assumptions, leading to several unspecified free parameters and domain assumptions typical in financial modeling.

free parameters (2)
  • volatility adjustment parameters in momentum filter
    Specific thresholds or adjustments for identifying trend strength are not detailed but are central to the filter.
  • correlation thresholds in minimax algorithm
    Parameters controlling structural diversification are implied but not specified.
axioms (2)
  • domain assumption Historical market data from 2006-2025 is representative of future market behavior including regime shifts.
    Invoked in the empirical validation via walk-forward backtest.
  • standard math SLSQP optimization can reliably find allocations that maximize Sortino ratio without local optima issues.
    Assumed in the use of the optimizer for capital allocation.
invented entities (1)
  • AEGIS framework no independent evidence
    purpose: To reengineer the trade-off between growth and stability in momentum strategies
    Newly proposed system without external validation beyond the described backtest.

pith-pipeline@v0.9.0 · 5785 in / 1773 out tokens · 84899 ms · 2026-05-21T01:44:28.236102+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

54 extracted references · 54 canonical work pages

  1. [1]

    Returns to buying winners and selling losers: Implications for stock market efficiency,

    N. Jegadeesh and S. Titman, “Returns to buying winners and selling losers: Implications for stock market efficiency,”The Journal of Finance, vol. 48, no. 1, pp. 65–91, 1993

    work page 1993

  2. [2]

    Value and momentum everywhere,

    C. S. Asness, T. J. Moskowitz, and L. H. Pedersen, “Value and momentum everywhere,”The Journal of Finance, vol. 68, no. 3, pp. 929–985, 2013

    work page 2013

  3. [3]

    Two centuries of price return momentum,

    C. Geczy and M. Samonov, “Two centuries of price return momentum,” Financial Analysts Journal, vol. 72, no. 5, pp. 32–56, 2016

    work page 2016

  4. [4]

    Efficient capital markets: A review of theory and empirical work,

    E. F. Fama, “Efficient capital markets: A review of theory and empirical work,”The Journal of Finance, vol. 25, no. 2, pp. 383–417, 1970

    work page 1970

  5. [5]

    Prospect theory: An analysis of decision under risk,

    D. Kahneman and A. Tversky, “Prospect theory: An analysis of decision under risk,”Econometrica, vol. 47, no. 2, pp. 263–291, 1979

    work page 1979

  6. [6]

    Investor psychology and security market under- and overreactions,

    K. Daniel, D. Hirshleifer, and A. Subrahmanyam, “Investor psychology and security market under- and overreactions,”The Journal of Finance, vol. 53, no. 6, pp. 1839–1885, 1998

    work page 1998

  7. [7]

    The adaptive markets hypothesis,

    A. W. Lo, “The adaptive markets hypothesis,”The Journal of Portfolio Management, vol. 30, no. 5, pp. 15–29, 2004

    work page 2004

  8. [8]

    A model of investor sentiment,

    N. Barberis, A. Shleifer, and R. Vishny, “A model of investor sentiment,” Journal of Financial Economics, vol. 49, no. 3, pp. 307–343, 1998

    work page 1998

  9. [9]

    A unified theory of underreaction, momentum trading, and overreaction in asset markets,

    H. Hong and J. C. Stein, “A unified theory of underreaction, momentum trading, and overreaction in asset markets,”The Journal of Finance, vol. 54, no. 6, pp. 2143–2184, 1999

    work page 1999

  10. [10]

    Optimal investment, growth options, and security returns,

    J. B. Berk, R. C. Green, and V . Naik, “Optimal investment, growth options, and security returns,”The Journal of Finance, vol. 54, no. 5, pp. 1553–1607, 1999

    work page 1999

  11. [11]

    Momentum crashes,

    K. Daniel and T. J. Moskowitz, “Momentum crashes,”Journal of Financial Economics, vol. 122, no. 2, pp. 221–247, 2016

    work page 2016

  12. [12]

    Momentum trading, return chasing, and predictable crashes,

    B. Chabot, E. Ghysels, and R. Jagannathan, “Momentum trading, return chasing, and predictable crashes,” National Bureau of Economic Research, Working Paper w20660, 2014

    work page 2014

  13. [13]

    Portfolio selection,

    H. Markowitz, “Portfolio selection,”The Journal of Finance, vol. 7, no. 1, pp. 77–91, 1952

    work page 1952

  14. [14]

    Capital asset prices: A theory of market equilibrium under conditions of risk,

    W. F. Sharpe, “Capital asset prices: A theory of market equilibrium under conditions of risk,”The Journal of Finance, vol. 19, no. 3, pp. 425–442, 1964

    work page 1964

  15. [15]

    Downside risk,

    F. A. Sortino and R. Van der Meer, “Downside risk,”The Journal of Portfolio Management, vol. 17, no. 4, pp. 27–31, 1991

    work page 1991

  16. [16]

    The markowitz optimization enigma: Is ‘optimized’ optimal?

    R. O. Michaud, “The markowitz optimization enigma: Is ‘optimized’ optimal?”Financial Analysts Journal, vol. 45, no. 1, pp. 31–42, 1989

    work page 1989

  17. [17]

    Bookstaber,A Demon of Our Own Design: Markets, Hedge Funds, and the Perils of Financial Innovation

    R. Bookstaber,A Demon of Our Own Design: Markets, Hedge Funds, and the Perils of Financial Innovation. John Wiley & Sons, 2007

    work page 2007

  18. [18]

    The variation of certain speculative prices,

    B. B. Mandelbrot, “The variation of certain speculative prices,”The Journal of Business, vol. 36, no. 4, pp. 394–419, 1963

    work page 1963

  19. [19]

    Coherent measures of risk,

    P. Artzner, F. Delbaen, J. M. Eber, and D. Heath, “Coherent measures of risk,”Mathematical Finance, vol. 9, no. 3, pp. 203–228, 1999

    work page 1999

  20. [20]

    N. N. Taleb,The Black Swan: The impact of the highly improbable. Random House, 2007

    work page 2007

  21. [21]

    Empirical properties of asset returns: stylized facts and statistical issues,

    R. Cont, “Empirical properties of asset returns: stylized facts and statistical issues,”Quantitative Finance, vol. 1, no. 2, pp. 223–236, 2001

    work page 2001

  22. [22]

    N. N. Taleb,Antifragile: Things that gain from disorder. Random House, 2012

    work page 2012

  23. [23]

    S&p u.s. indices methodology,

    S&P Dow Jones Indices, “S&p u.s. indices methodology,” S&P Global, Tech. Rep., 2023

    work page 2023

  24. [24]

    Nasdaq-100 index methodology,

    Nasdaq, Inc., “Nasdaq-100 index methodology,” Nasdaq Global Indexes, Tech. Rep., 2023

    work page 2023

  25. [25]

    Data structures for statistical computing in python,

    W. McKinney, “Data structures for statistical computing in python,” in Proceedings of the 9th Python in Science Conference, 2010, pp. 51–56

    work page 2010

  26. [26]

    Historical data api,

    Yahoo! Finance, “Historical data api,” Yahoo! Inc., 2026

    work page 2026

  27. [27]

    International momentum strategies,

    K. G. Rouwenhorst, “International momentum strategies,”The Journal of Finance, vol. 53, no. 1, pp. 267–284, 1998

    work page 1998

  28. [28]

    Time series momen- tum,

    T. J. Moskowitz, Y . H. Ooi, and L. H. Pedersen, “Time series momen- tum,”Journal of Financial Economics, vol. 104, no. 2, pp. 228–250, 2012

    work page 2012

  29. [29]

    A minimax portfolio selection rule with linear program- ming solution,

    M. R. Young, “A minimax portfolio selection rule with linear program- ming solution,”Management Science, vol. 44, no. 5, pp. 673–683, 1998

    work page 1998

  30. [30]

    Toward maximum diversification,

    Y . Choueifaty and Y . Coignard, “Toward maximum diversification,”The Journal of Portfolio Management, vol. 35, no. 1, pp. 40–51, 2008

    work page 2008

  31. [31]

    Optimal versus naive diver- sification: How inefficient is the 1/n portfolio strategy?

    V . DeMiguel, L. Garlappi, and R. Uppal, “Optimal versus naive diver- sification: How inefficient is the 1/n portfolio strategy?”The Review of Financial Studies, vol. 22, no. 5, pp. 1915–1953, 2009

    work page 1915

  32. [32]

    Minimum-variance portfolios in the us equity market,

    R. Clarke, H. de Silva, and S. Thorley, “Minimum-variance portfolios in the us equity market,”The Journal of Portfolio Management, vol. 33, no. 1, pp. 10–24, 2006

    work page 2006

  33. [33]

    A software package for sequential quadratic programming,

    D. Kraft, “A software package for sequential quadratic programming,” DFVLR, Forschungsbericht, Tech. Rep., 1988

    work page 1988

  34. [34]

    Scipy 1.0: fundamental algorithms for scientific computing in python,

    P. Virtanen, R. Gommers, T. E. Oliphantet al., “Scipy 1.0: fundamental algorithms for scientific computing in python,”Nature Methods, vol. 17, no. 3, pp. 261–272, 2020

    work page 2020

  35. [35]

    Boyd and L

    S. Boyd and L. Vandenberghe,Convex Optimization. Cambridge University Press, 2004

    work page 2004

  36. [36]

    Performance measurement in a downside risk framework,

    F. A. Sortino and L. N. Price, “Performance measurement in a downside risk framework,”The Journal of Investing, vol. 3, no. 3, pp. 59–64, 1994

    work page 1994

  37. [37]

    Optimal rules for ordering uncertain prospects,

    V . S. Bawa, “Optimal rules for ordering uncertain prospects,”Journal of Financial Economics, vol. 2, no. 1, pp. 95–121, 1975

    work page 1975

  38. [38]

    Mean-risk analysis with risk associated with below- target returns,

    P. C. Fishburn, “Mean-risk analysis with risk associated with below- target returns,”The American Economic Review, vol. 67, no. 2, pp. 116– 126, 1977

    work page 1977

  39. [39]

    Pardo,The evaluation and optimization of trading strategies

    R. Pardo,The evaluation and optimization of trading strategies. John Wiley & Sons, 2008

    work page 2008

  40. [40]

    Survivorship bias in performance studies,

    S. J. Brown, W. N. Goetzmann, R. G. Ibbotson, and S. A. Ross, “Survivorship bias in performance studies,”The Review of Financial Studies, vol. 5, no. 4, pp. 553–580, 1992

    work page 1992

  41. [41]

    Lopez de Prado,Advances in financial machine learning

    M. Lopez de Prado,Advances in financial machine learning. John Wiley & Sons, 2018

    work page 2018

  42. [42]

    Maximum drawdown,

    M. Magdon-Ismail and A. F. Atiya, “Maximum drawdown,”Risk Mag- azine, vol. 17, no. 10, pp. 99–102, 2004

    work page 2004

  43. [43]

    Calmar ratio: A smoother tool,

    T. W. Young, “Calmar ratio: A smoother tool,”Futures, vol. 20, no. 1, p. 40, 1991

    work page 1991

  44. [44]

    Post-modern portfolio theory comes of age,

    B. M. Rom and K. W. Ferguson, “Post-modern portfolio theory comes of age,”The Journal of Investing, vol. 3, no. 3, pp. 11–17, 1994

    work page 1994

  45. [45]

    Pseudo-mathematics and financial charlatanism: The effects of backtest overfitting on out-of-sample performance,

    D. H. Bailey, J. M. Borwein, M. Lopez de Prado, and Q. J. Zhu, “Pseudo-mathematics and financial charlatanism: The effects of backtest overfitting on out-of-sample performance,”Notices of the AMS, vol. 61, no. 5, pp. 458–471, 2014

    work page 2014

  46. [46]

    Data-snooping biases in tests of financial asset pricing models,

    A. W. Lo and A. C. MacKinlay, “Data-snooping biases in tests of financial asset pricing models,”The Review of Financial Studies, vol. 3, no. 3, pp. 431–467, 1990

    work page 1990

  47. [47]

    The cross-section of expected stock returns,

    E. F. Fama and K. R. French, “The cross-section of expected stock returns,”The Journal of Finance, vol. 47, no. 2, pp. 427–465, 1992

    work page 1992

  48. [48]

    The relationship between return and market value of common stocks,

    R. W. Banz, “The relationship between return and market value of common stocks,”Journal of Financial Economics, vol. 9, no. 1, pp. 3–18, 1981

    work page 1981

  49. [49]

    Size matters, if you control your junk,

    C. S. Asness, A. Frazzini, R. Israel, T. J. Moskowitz, and L. H. Pedersen, “Size matters, if you control your junk,”Journal of Financial Economics, vol. 129, no. 3, pp. 479–509, 2018

    work page 2018

  50. [50]

    Tail risk and asset prices,

    B. Kelly and H. Jiang, “Tail risk and asset prices,”The Review of Financial Studies, vol. 27, no. 10, pp. 2841–2871, 2014

    work page 2014

  51. [51]

    Risk parity portfolios: Efficient portfolios through true diver- sification,

    E. Qian, “Risk parity portfolios: Efficient portfolios through true diver- sification,” PanAgora Asset Management, Tech. Rep., 2005. 18

    work page 2005

  52. [52]

    Leverage aversion and risk parity,

    C. S. Asness, A. Frazzini, and L. H. Pedersen, “Leverage aversion and risk parity,”Financial Analysts Journal, vol. 68, no. 1, pp. 47–59, 2012

    work page 2012

  53. [53]

    The properties of equally weighted risk contribution portfolios,

    S. Maillard, T. Roncalli, and J. Te ¨ıletche, “The properties of equally weighted risk contribution portfolios,”The Journal of Portfolio Man- agement, vol. 36, no. 4, pp. 60–70, 2010

    work page 2010

  54. [54]

    and the cross-section of expected returns,

    C. R. Harvey, Y . Liu, and H. Zhu, “. . . and the cross-section of expected returns,”The Review of Financial Studies, vol. 29, no. 1, pp. 5–68, 2016

    work page 2016