Paper: arXiv 2411.15712

Authors: Yong Li

Abstract

Providing optimal portfolio selection for investors has always been one of the hot topics in academia. In view of the traditional portfolio model could not adapt to the actual capital market and can provide erroneous results. This paper innovatively constructs a mean-detrended cross-correlation portfolio model (M-DCCP model), This model is designed to embed detrended cross-correlation between different simultaneously recorded time series in the presence of nonstationary into the reward-risk criterion. We illustrate the model’s effectiveness by selected five composite indexes (SSE 50, CSI 300, SSE 500, CSI 1000 and CSI 2000) in China A-share market. The empirical results show that compared with traditional mean-variance portfolio model (M-VP model), the M-DCCP model is more conducive for investors to construct optimal portfolios under the different fluctuation exponent preference and time scales preference, so as to improve portfolio’s performance.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper is mathematically dense with advanced multifractal techniques, DCCA, and derivations, earning a high math score. It has a clear empirical test using real Chinese market data (five indices) and compares results to a benchmark, giving it solid but not exhaustive empirical rigor.

Research Flowchart

  flowchart TD
  A["Research Goal: Construct optimal portfolio<br>adapting to nonstationary markets"] --> B["Data: Five China A-share indexes<br>SSE 50, CSI 300, SSE 500, CSI 1000, CSI 2000"]
  B --> C["Methodology: M-DCCP Model<br>Embedding Detrended Cross-Correlation"]
  C --> D["Methodology: Mean-Variance Model<br>Traditional Benchmark"]
  C --> E{"Computational Process"}
  D --> E
  E --> F["Evaluation: Risk/Return analysis<br>across time scales & fluctuation exponents"]
  F --> G["Outcome: M-DCCP outperforms<br>traditional models for investors"]
  G --> H["Conclusion: Improved portfolio<br>performance in nonstationary markets"]

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 mean‑detrended cross‑correlation portfolio model (M‑DCCP) that embeds detrended cross‑correlation into the reward‑risk criterion.

Source sentence
This paper innovatively constructs a mean-detrended cross-correlation portfolio model (M-DCCP model), This model is designed to embed detrended cross-correlation between different simultaneously recorded time series in the presence of nonstationary into the reward-risk criterion.

Assumes 3

  • Portfolio P consists of N risky assets. model
    Source sentence
    Let’s still assume that portfolio P consists of N risky assets, ri represents the expected return rate of asset i, rF represents the risk-free return rate, and ωi(q, s) represents the weight of asset i.
  • The multifractal detrended cross‑correlation function Fij(q,s) can replace traditional covariance in the reward‑risk criterion. statistical
    Source sentence
    Therefore, it is reasonable and feasible to replace traditional covariance with Fij(q,s) in reward-risk criterion.
  • Risk‑free return rate rF is available. market
    Source sentence
    rF represents the risk-free return rate

Data

Backtest sample: China A-share composite indexes · equities · daily

  • SSE 50 index · Wind databases market-prices commercial
    2015-01-01 to 2023-12-31 · China A‑share large‑cap stocks
    Source sentence
    The sample period is from January 1, 2015 to December 31, 2023.
  • CSI 300 index · Wind databases market-prices commercial
    2015-01-01 to 2023-12-31 · China A‑share large‑cap stocks
    Source sentence
    The sample period is from January 1, 2015 to December 31, 2023.
  • CSI 500 index · Wind databases market-prices commercial
    2015-01-01 to 2023-12-31 · China A‑share mid‑cap stocks
    Source sentence
    The sample period is from January 1, 2015 to December 31, 2023.
  • CSI 1000 index · Wind databases market-prices commercial
    2015-01-01 to 2023-12-31 · China A‑share small‑cap stocks
    Source sentence
    The sample period is from January 1, 2015 to December 31, 2023.
  • CSI 2000 index · Wind databases market-prices commercial
    2015-01-01 to 2023-12-31 · China A‑share micro‑cap stocks
    Source sentence
    The sample period is from January 1, 2015 to December 31, 2023.

Costs

Not modeled A trading or execution result is reported without costs.

Finds 2

  • The M‑DCCP model generally outperforms the traditional mean‑variance (M‑VP) model in portfolio performance for the five Chinese A‑share indices. performance
    Source sentence
    The empirical analysis of the SSE 50, CSI 300, CSI 500, CSI 1000 and CSI 2000 indices of China A-share market shows that the performance of the M-DCCP model is generally superior to that of the M-VP model, indicating that the M-DCCP model is effective.
  • The M‑DCCP model better accommodates investors' preferences for different fluctuation exponents and time scales, improving portfolio performance compared with the M‑VP model. performance
    Source sentence
    The empirical results show that compared with traditional mean-variance portfolio model (M-VP model), the M-DCCP model is more conducive for investors to construct optimal portfolios under the different fluctuation exponent preference and time scales preference, so as to improve portfolio’s performance.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 11 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.