Paper: arXiv 2511.16339

Authors: Miquel Noguer i Alonso

Abstract

This paper introduces a comprehensive framework for Financial Information Theory by applying information-theoretic concepts such as entropy, Kullback-Leibler divergence, mutual information, normalized mutual information, and transfer entropy to financial time series. We systematically derive these measures with complete mathematical proofs, establish their theoretical properties, and propose practical algorithms for estimation. Using S&P 500 data from 2000 to 2025, we demonstrate empirical usefulness for regime detection, market efficiency testing, and portfolio construction. We show that normalized mutual information (NMI) behaves as a powerful, bounded, and interpretable measure of temporal dependence, highlighting periods of structural change such as the 2008 financial crisis and the COVID-19 shock. Our entropy-adjusted Value at Risk, information-theoretic diversification criterion, and NMI-based market efficiency test provide actionable tools for risk management and asset allocation. We interpret NMI as a quantitative diagnostic of the Efficient Market Hypothesis and demonstrate that information-theoretic methods offer superior regime detection compared to traditional autocorrelation- or volatility-based approaches. All theoretical results include rigorous proofs, and empirical findings are validated across multiple market regimes spanning 25 years of daily returns.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents advanced information theory with rigorous proofs and theorems (high math complexity), while also demonstrating empirical validation on S&P 500 data over 25 years with practical algorithms for estimation and application (high empirical rigor).

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Develop Financial Information Theory<br>using information-theoretic measures"] --> B["Methodology: Derive & Prove<br>Entropy, KL Divergence, Mutual Info, NMI, Transfer Entropy"]
  B --> C["Data Input:<br>S&P 500 Daily Returns<br>2000-2025"]
  C --> D["Computational Processes:<br>Algorithmic Estimation of Metrics<br>& Sequential Application"]
  D --> E{"Key Findings & Outcomes"}
  E --> F["1. NMI for Regime Detection<br>Identifies 2008 & 2021 Structural Shifts"]
  E --> G["2. Entropy-Adjusted VaR<br>Superior Risk Management Tool"]
  E --> H["3. NMI Market Efficiency Test<br>Quantifies EMH violations<br>vs. Autocorrelation"]
  E --> I["4. Info-Theoretic Diversification<br>Optimized Portfolio Construction"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a comprehensive Financial Information Theory framework with practical k‑NN estimation algorithms and applications such as entropy‑adjusted VaR, information‑theoretic diversification, and NMI‑based market efficiency testing.

Source sentence
practical algorithms for estimating these quantities in financial time series using k‑NN methods with detailed implementation guidelines

Assumes 4

  • The empirical analysis uses daily returns of the S&P 500 constituents from 2000 to 2025. data
    Source sentence
    Using S&P 500 data (2000–2025), we show how entropy, KL divergence, and NMI capture major market regimes
  • k‑nearest‑neighbor estimators require a choice of k and window length; small windows increase variance while large windows smooth short‑lived regimes. statistical
    Source sentence
    k‑nearest‑neighbor (k‑NN) estimators are sensitive to the choice of k and window length: small windows increase variance and finite‑sample noise, whereas large windows smooth over short‑lived regimes
  • The market is sufficiently liquid to compute the information‑theoretic measures in real‑time with rolling windows. market
    Source sentence
    All three measures can be computed in real‑time with rolling windows, enabling adaptive risk management, dynamic model retraining, and systematic trading strategies
  • The Efficient Market Hypothesis implies that NMI should be close to zero under normal conditions. model
    Source sentence
    past returns should not contain exploitable information about future returns, implying that NMI(rt+h; It) should be close to zero

Data

  • S&P 500 daily returns market-prices public
    2000–2025 · S&P 500 constituents
    Source sentence
    Using S&P 500 data (2000–2025), we show how entropy, KL divergence, and NMI capture major market regimes

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • NMI remains near zero 77.9% of the time, confirming market efficiency during normal periods. statistical
    Source sentence
    NMI remains near zero 77.9% of the time, validating the EMH during normal market periods
  • NMI spikes during crises, correctly identifying the 2008–2009 financial crisis and the COVID‑19 pandemic as periods of temporary market inefficiency. performance
    Source sentence
    NMI spikes during crises, correctly identifying the 2008–2009 financial crisis, COVID‑19 pandemic, and other major disruptions as periods of temporary market inefficiency
  • KL divergence effectively detects distributional regime shifts, providing superior regime detection compared to volatility‑based methods. performance
    Source sentence
    KL divergence effectively detects distributional regime shifts, providing superior regime detection compared to volatility‑based methods
  • Entropy captures uncertainty dynamics with clear correspondence to known market stress events. statistical
    Source sentence
    Entropy captures uncertainty dynamics, with clear correspondence to known market stress events
  • Information‑theoretic methods are distribution‑free, capture nonlinear dependencies, and are scale‑invariant, offering advantages over traditional approaches. theoretical
    Source sentence
    Information‑theoretic methods offer several advantages over traditional approaches

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 73 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (18)

  1. Empirical Properties of Asset Returns: Stylized Facts and Statistical Issues (2001) — link
  2. Elements of Information Theory (2006)
  3. The Adaptive Markets Hypothesis: Market Efficiency from an Evolutionary Perspective (2004)
  4. Efficient Capital Markets: A Review of Theory and Empirical Work (1970) — link
  5. Efficient Capital Markets: II (1991) — link
  6. Stock Returns and the Weekend Effect (1980) — link
  7. Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency (1993) — link
  8. Some Anomalous Evidence Regarding Market Efficiency (1978) — link
and 10 more
  1. Sample Estimate of the Entropy of a Random Vector (1987)
  2. Entropy-Based Market Efficiency Testing in Global Financial Markets (2021) — link
  3. Quantitative Risk Management: Concepts, Techniques and Tools (2015)
  4. Machine Learning in Asset Pricing (2024)
  5. Information Theory and Efficient Market Hypothesis (2024) — link
  6. Information-Theoretic Measures of Market Efficiency: A Global Analysis (2022) — link
  7. Information and Information Stability of Random Variables and Processes (1964)
  8. A Mathematical Theory of Communication (1948) — link
  9. Do Stock Prices Move Too Much to be Justified by Subsequent Changes in Dividends? (1981)
  10. The Limits of Arbitrage (1997) — link

0 of 18 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.