Paper: arXiv 2406.00610

Authors: Qiqin Zhou

Abstract

The measure of portfolio risk is an important input of the Markowitz framework. In this study, we explored various methods to obtain a robust covariance estimators that are less susceptible to financial data noise. We evaluated the performance of large-cap portfolio using various forms of Ledoit Shrinkage Covariance and Robust Gerber Covariance matrix during the period of 2012 to 2022. Out-of-sample performance indicates that robust covariance estimators can outperform the market capitalization-weighted benchmark portfolio, particularly during bull markets. The Gerber covariance with Mean-Absolute-Deviation (MAD) emerged as the top performer. However, robust estimators do not manage tail risk well under extreme market conditions, for example, Covid-19 period. When we aim to control for tail risk, we should add constraint on Conditional Value-at-Risk (CVaR) to make more conservative decision on risk exposure. Additionally, we incorporated unsupervised clustering algorithm K-means to the optimization algorithm (i.e. Nested Clustering Optimization, NCO). It not only helps mitigate numerical instability of the optimization algorithm, but also contributes to lower drawdown as well.

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 employs advanced statistical methods like Ledoit-Wolf shrinkage, robust covariance estimators (Gerber), and CVaR constraints requiring semidefinite optimization, reflecting high mathematical density. It also demonstrates strong empirical rigor by backtesting on a decade of data, comparing benchmarks, and integrating unsupervised clustering (K-means) to improve implementation stability.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Robust Portfolio Optimization"] --> B["Data Input:<br>Large-cap Equities 2012-2022"]
  B --> C["Methodology I:<br>Robust Covariance Estimators<br>Ledoit-Shrinkage vs. Gerber-MAD"]
  B --> D["Methodology II:<br>CVaR Constraints & Nested Clustering Optimization NCO"]
  C --> E["Computational Process:<br>Out-of-sample Backtesting"]
  D --> E
  E --> F{"Key Outcomes"}
  F --> G["Gerber-MAD Covariance<br>Top Performer in Bull Markets"]
  F --> H["Robust Estimators alone<br>Fail during Extreme Events<br>e.g., Covid-19"]
  F --> I["CVaR + NCO Integration<br>Controls Tail Risk &<br>Reduces Drawdowns"]

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 using robust covariance estimators combined with a CVaR constraint and a Nested Clustering Optimization (NCO) algorithm to improve minimum‑variance portfolio performance.

Source sentence
we incorporated unsupervised clustering algorithm K-means to the optimization algorithm (i.e. Nested Clustering Optimization, NCO).

Assumes 5

  • Portfolios are re‑balanced on a weekly basis. execution
    Source sentence
    Our portfolios are re-balanced weekly and all data are sampled weekly so that we do not need to adjust our estimation of asset return and covariance.
  • Historical weekly returns are used as the sample space for CVaR calculation with equal probability. model
    Source sentence
    In the CVaR constraint, 𝜔 is an event in the sample space Ω with probability P(𝑤). We use historical return sample as the sample space and define P to be 1/T.
  • Transaction costs are a flat 50 basis points per trade. execution
    Source sentence
    The transaction cost is set to be 50 basis points for both purchasing and selling.
  • The covariance matrix can be de‑noised using the method described in section 3.2.3. statistical
    Source sentence
    We performed de‑noising method mentioned in section 3.2.3 on sample covariance to obtain the de‑noised covariance matrix.
Show 1 more
  • Short‑sales are prohibited (short‑sales constraints). market
    Source sentence
    The first approach is to introduce strong constraints on weights, such as short‑sales constraints [3] (Frost and Savarino, 1988).

Data

Backtest sample: 2019-01 – 2021-01 · 55 S&P 500 Large Cap equities · equities · weekly

  • S&P500 equities · Yahoo Finance market-prices public
    January 2012 to January 2022 · S&P500 large‑cap equities
    Source sentence
    We collected data of S&P500 equities over the time period January 2012 to January 2022 as well as sector information from yahoo finance.

Recognised sources: Yahoo Finance

Costs

Modeled Costs are part of the reported headline results.

50 basis points per side, applied to all portfolio turnover calculations.

Source sentence
The transaction cost is set to be 50 basis points for both purchasing and selling.

Finds 5

Reported performance (Gerber MAD minimum variance portfolio with CVaR constraint): Sharpe 1.45 · annual return 40.5% · max drawdown 22.9%

  • Robust covariance estimators, especially Gerber covariance with MAD, outperform the market‑cap weighted benchmark in out‑of‑sample Sharpe ratio, particularly in bull markets. performance
    Source sentence
    Out‑of‑sample performance indicates that robust covariance estimators can outperform the market capitalization‑weighted benchmark portfolio, particularly during bull markets. The Gerber covariance with Mean‑Absolute‑Deviation (MAD) emerged as the top performer.
  • Adding a CVaR constraint reduces maximum draw‑down by more than 2% compared with a single‑CVaR constraint portfolio. performance
    Source sentence
    the most significant improvement is max draw‑down: 2‑CVaR constraint minimum variance portfolios have more than 2% lower max draw‑down than the 1‑CVaR constraint portfolio.
  • Nested Clustering Optimization lowers portfolio volatility and maximum draw‑down by about 5% while increasing transaction costs modestly. performance
    Source sentence
    the resulting minimum variance portfolio with NCO decreases the maximum drawdown
  • All three covariance measures (Exponentially Weighted, Ledoit Shrinkage, Robust Gerber) achieve higher Sharpe ratios than the market‑cap benchmark but exhibit higher volatility during bear periods. performance
    Source sentence
    Out‑of‑sample performance shows that all three covariance measures outperform the market capitalization‑weighted benchmark in terms of the Sharpe ratio
  • Turnover rates across minimum‑variance portfolios are similar, averaging around 8% weekly, suggesting ℓ1 regularization helps control transaction costs. statistical
    Source sentence
    we also calculated the average daily turnover rate and we found that all portfolios have around 8% turnover rate.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 24 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 2 papers in the archive (1 by independent authors): A Novel approach to portfolio construction (discusses its findings)

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.