Paper: arXiv 2407.01550
Authors: Maysam Khodayari Gharanchaei, Prabhu Prasad Panda, Xilin Chen
Abstract
This paper focuses on the developing of high-dimensional risk models to construct portfolios of securities in the US stock exchange. Investors seek to gain the highest profits and lowest risk in capital markets. We have developed various risk models and for each model different investment strategies are tested. Out of sample tests are performed on a long-term horizon from 1970 until 2023.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 6.0/10 (capped from 9.0: transaction costs not modelled; see penalty flags)
- Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 9.0)
Why this score: The paper employs advanced mathematical models with multiple covariance estimators and complex optimization formulations (e.g., risk parity with logarithmic objectives), indicating high mathematical sophistication. It demonstrates high empirical rigor through detailed backtesting on real CRSP data over a 50+ year horizon, using multiple performance metrics, out-of-sample testing, and implementation details like specific optimization solvers.
Research Flowchart
flowchart TD A["Research Goal: Construct Optimal Portfolios<br>via High-Dimensional Risk Models"] --> B["Data: US Stocks 1970-2023"] B --> C["Develop Risk Models<br>Factor Models & Covariance Estimators"] C --> D["Define Strategies<br>Long-Short & Optimization"] D --> E["Out-of-Sample Testing<br>1970-2023 Horizon"] E --> F["Key Outcomes:<br>Performance & Risk Metrics"] F --> G["Conclusion:<br>Model Efficacy for US Equities"]
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 develops various high‑dimensional risk models and tests different investment strategies based on them.
Source sentence
We have developed various risk models and for each model different investment strategies are tested.
Assumes 3
- Portfolios are long‑only and fully invested. model
Source sentence
All portfolios in this project are characterized as long-only and fully invested (Barberis et al., 2015) (Fama and French, 1993).
- Adjusted returns exclude dividend effects. data
Source sentence
Adjusted returns (Ferson and Harvey, 1999), excluding the effects of dividends, were used to enhance data accuracy (Freyberger et al., 2020).
- Covariance matrices are estimated using the past 60 months of excess returns. statistical
Source sentence
... of the past 60 monthly excess returns and market excess returns
Data
- CRSP dataset market-prices commercial
Source sentence
The dataset utilized in this research is sourced from the CRSP dataset, focusing on risky US stocks.
Costs
Not modeled
Finds 2
- The maximum diversification portfolio consistently outperformed other strategies, especially in Sharpe ratio. performance
Source sentence
... the study revealed that the maximum diversification portfolio consistently outperformed other portfolio strategies. This superior performance is notably reflected in the Sharpe ratio.
- Constructing risk parity portfolios is challenging when using the sample covariance estimator with shrinkage. negative
Source sentence
A noteworthy revelation is the challenge encountered in constructing risk parity portfolios under the sample covariance estimator with shrinkage.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 12 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.