Paper: arXiv 2602.20856

Authors: Doron Avramov, Xin He

Abstract

This paper develops a unified framework that links firm-level predictive signals, cross-asset spillovers, and the stochastic discount factor (SDF). Signals and spillovers are jointly estimated by maximizing the Sharpe ratio, yielding an interpretable SDF that both ranks characteristic relevance and uncovers the direction of predictive influence across assets. Out-of-sample, the SDF consistently outperforms self-predictive and expected-return benchmarks across investment universes and market states. The inferred information network highlights large, low-turnover firms as net transmitters. The framework offers a clear, economically grounded view of the informational architecture underlying cross-sectional return dynamics.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 6.0/10 (capped from 8.5: transaction costs not modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents a novel framework integrating cross-asset spillovers directly into stochastic discount factor (SDF) construction and maximum-Sharpe ratio optimal portfolios. The empirical execution is exceptionally rigorous, utilizing comprehensive datasets (138 firm characteristics across multi-decade samples) and out-of-sample rolling validations across diverse market regimes.

Research Flowchart

  flowchart TD
    A[Research Goal: Link firm signals, cross-asset spillovers & SDF] --> B[Inputs: Firm-level characteristics & cross-asset market data]
    B --> C[Methodology: Jointly estimate signals & spillovers via Sharpe Ratio Maximization]
    C --> D[Computational Process: Out-of-sample testing & information network inference]
    D --> E[Outcomes: Outperforms benchmarks & reveals large/low-turnover firms as net transmitters]

Cited References (97)

  1. Principal portfolios (2023)
  2. The virtue of complexity in return prediction (2024)
  3. The conditional CAPM does not explain asset-pricing anomalies (2006)
  4. When are contrarian profits due to stock market overreaction? (1990)
  5. The sampling error in estimates of mean-variance efficient portfolio weights (1999)
  6. On the representation of continuous functions of seversal variables by superpositions of continuous functions of a smaller number of variables. (1956)
  7. On functions of three variables. (1957)
  8. Is there a replication crisis in finance? (2023)
and 89 more
  1. Do industries lead stock markets? (2007)
  2. Predicting stock returns (2006)
  3. The characteristics that provide independent information about average US monthly stock returns (2017)
  4. Does academic research destroy stock return predictability? (2016)
  5. Trading volume and cross-autocorrelations in stock returns (2000)
  6. Industry costs of equity (1997) — link
  7. Random Features for Large-Scale Kernel Machines (2007)
  8. Liquidity and stock returns: An alternative test (1998)
  9. Machine learning vs. economic restrictions: Evidence from stock return predictability (2023)
  10. Machine learning and the implementable efficient frontier (2024)
  11. Common risk factors in the returns on stocks and bonds (1993)
  12. Replicating anomalies (2020)
  13. Industry information diffusion and the lead-lag effect in stock returns (2007)
  14. Sparse signals in the cross-section of returns (2019)
  15. Liquidity risk and expected stock returns (2003)
  16. Short- and long-horizon behavioral factors (2020)
  17. Digesting anomalies: An investment approach (2015)
  18. Mispricing factors (2017)
  19. A five-factor asset pricing model (2015)
  20. Investor sentiment and the cross-section of stock returns (2006)
  21. On the network topology of variance decompositions: Measuring the connectedness of financial firms (2014)
  22. Economic links and predictable returns (2008)
  23. Complicated firms (2012)
  24. Empirical asset pricing via machine learning (2020)
  25. Autoencoder asset pricing models (2021)
  26. Deep learning in characteristics-sorted factor models (2024)
  27. Growing the efficient frontier on panel trees (2025)
  28. Deep learning in asset pricing (2024)
  29. A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix (1987)
  30. Cross-stock momentum and factor momentum (2023)
  31. A frog in every pan: Information discreteness and the lead-lag returns puzzle (2022)
  32. Psychological barrier and cross-firm return predictability (2021)
  33. Economic Links from Bonds and Cross-Stock Return Predictability (2025)
  34. A test of the efficiency of a given portfolio (1989)
  35. Presidential address: Discount rates (2011)
  36. … and the cross-section of expected returns (2016)
  37. Transmission of volatility between stock markets (1990)
  38. Correlations in price changes and volatility across international stock markets (1990)
  39. Information and volatility linkages in the stock, bond, and money markets (1998)
  40. Exchange rates, equity prices, and capital flows (2006)
  41. Structural breaks in volatility spillovers between international financial markets: contagion or mere interdependence? (2014)
  42. Measuring financial asset return and volatility spillovers, with application to global equity markets (2009)
  43. Better to give than to receive: Predictive directional measurement of volatility spillovers (2012)
  44. Financial contagion and network analysis (2013)
  45. No contagion, only interdependence: measuring stock market comovements (2002)
  46. Information and volatility: The no-arbitrage martingale approach to timing and resolution irrelevancy (1989)
  47. Characteristics are covariances: A unified model of risk and return (2019)
  48. Factors that fit the time series and cross-section of stock returns (2020)
  49. Real asset illiquidity and the cost of capital (2014)
  50. Labor hiring, investment, and stock return predictability in the cross section (2014)
  51. Contrarian investment, extrapolation, and risk (1994)
  52. Accrual reliability, earnings persistence and stock prices (2005)
  53. The effect of personal taxes and dividends on capital asset prices: Theory and empirical evidence (1979)
  54. The cross-section of expected stock returns (1992)
  55. Implied equity duration: A new measure of equity risk (2004)
  56. Asset growth and the cross-section of stock returns (2008)
  57. Financial machine learning (2023)
  58. Taming the factor zoo: A test of new factors (2020)
  59. Illiquidity and stock returns: cross-section and time-series effects (2002)
  60. The use of DuPont analysis by market participants (2008)
  61. Is the risk of bankruptcy a systematic risk? (1998)
  62. Commonality in the determinants of expected stock returns (1996)
  63. Dividends and taxes: Some empirical evidence (1982)
  64. A simple way to estimate bid-ask spreads from daily high and low prices (2012)
  65. Arbitrage risk and the book-to-market anomaly (2003)
  66. Implications of security market data for models of dynamic economies (1991)
  67. The role of conditioning information in deducing testable restrictions implied by dynamic asset pricing models (1987)
  68. PORTFOLIO SELECTION (1952)
  69. Variable selection for portfolio choice (2001)
  70. Parametric portfolio policies: Exploiting characteristics in the cross-section of equity returns (2009)
  71. Dynamic portfolio selection by augmenting the asset space (2006)
  72. Asset pricing: Revised edition (2009)
  73. Asset pricing and portfolio choice theory: 2nd edition (2017)
  74. Graph Machine Learning for Asset Pricing: Traversing the Supply Chain and Factor Zoo (2025)
  75. One factor to bind the cross-section of returns — → 2404.08129
  76. Pricing Kernel in High Dimension: Factor Selection, Publication Bias and Relation to Corporate Bonds (2025)
  77. Principal Portfolios: The Multi-Signal Case (2024)
  78. Link Complexity and Cross-Predictability (2023)
  79. Maximizing the Sharpe Ratio: A Genetic Programming Approach (2025)
  80. Optimal Portfolio Choice with Economic Constraints: A Genetic Programming Approach (2024)
  81. Dual Industry Effects and Cross-Stock Predictability (2025)
  82. AlphaPortfolio: Direct construction through deep reinforcement learning and interpretable AI (2022)
  83. Schr"odinger’s Sparsity in the Cross Section of Stock Returns (2025)
  84. Can Machines Learn Weak Signals? (2024)
  85. APT or “AIPT”? The Surprising Dominance of Large Factor Models (2024)
  86. Artificial Intelligence Asset Pricing Models (2024)
  87. Universal portfolio shrinkage (2025)
  88. The Book-to-Price Effect in Stock Returns: Accounting for Leverage (2007) — link
  89. Persuasive Evidence of Market Inefficiency (1985) — link

1 of 97 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.