Paper: arXiv 2403.07998
Authors: Khizar Qureshi, Tauhid Zaman
Abstract
Pairs trading, a strategy that capitalizes on price movements of asset pairs driven by similar factors, has gained significant popularity among traders. Common practice involves selecting highly cointegrated pairs to form a portfolio, which often leads to the inclusion of multiple pairs sharing common assets. This approach, while intuitive, inadvertently elevates portfolio variance and diminishes risk-adjusted returns by concentrating on a small number of highly cointegrated assets. Our study introduces an innovative pair selection method employing graphical matchings designed to tackle this challenge. We model all assets and their cointegration levels with a weighted graph, where edges signify pairs and their weights indicate the extent of cointegration. A portfolio of pairs is a subgraph of this graph. We construct a portfolio which is a maximum weighted matching of this graph to select pairs which have strong cointegration while simultaneously ensuring that there are no shared assets within any pair of pairs. This approach ensures each asset is included in just one pair, leading to a significantly lower variance in the matching-based portfolio compared to a baseline approach that selects pairs purely based on cointegration. Theoretical analysis and empirical testing using data from the S&P 500 between 2017 and 2023, affirm the efficacy of our method. Notably, our matching-based strategy showcases a marked improvement in risk-adjusted performance, evidenced by a gross Sharpe ratio of 1.23, a significant enhancement over the baseline value of 0.48 and market value of 0.59. Additionally, our approach demonstrates reduced trading costs attributable to lower turnover, alongside minimized single asset risk due to a more diversified asset base.
Complexity vs Empirical Score
- Math Complexity: 6.0/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced graph theory (maximum weighted matching) and cointegration analysis, placing it in the higher math complexity range; it also provides concrete empirical results on S&P 500 data (2017-2023) with reported Sharpe ratios and turnover metrics, indicating strong backtest readiness.
Research Flowchart
flowchart TD
A["Research Goal: Optimize Pairs Trading Portfolio<br>by minimizing shared assets and variance"] --> B
subgraph B ["Methodology: Graph Theory Approach"]
direction LR
B1["Data: S&P 500 Stocks 2017-2023"] --> B2["Compute Cointegration Weights"] --> B3["Construct Weighted Graph<br>Nodes=Assets, Edges=Cointegration"] --> B4["Compute Maximum Weighted Matching<br>to Select Non-Overlapping Pairs"]
end
B --> C["Outcomes: Matching Portfolio"]
C --> D{"Performance Metrics"}
D --> E["Gross Sharpe Ratio: 1.23<br>vs 0.48 (Baseline) & 0.59 (Market)"]
D --> F["Lower Variance & Turnover<br>Minimized Single Asset Risk"]
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 matching‑based pair selection method that uses graph‑theoretic maximum weight matchings to choose cointegrated pairs with no shared assets.
Source sentence
We propose techniques from graph theory such as matchings, to determine subsets of pairs with no common assets.
Assumes 6
- All daily log‑normal price changes have the same mean µ1 and noise standard deviation σ1. model
Source sentence
To further simplify our analysis, we will assume all daily log-normal price changes have the same mean µ1 and noise standard deviation σ1
- All cointegrated spreads have the same standard deviation σ. model
Source sentence
and all cointegrated spreads have the same standard deviation σ.
- A unit amount is invested in each pair. execution
Source sentence
For each portfolio, we assume a unit amount is invested in each pair.
- Covariance is zero between any pairs that do not share a common stock. statistical
Source sentence
We assume the covariance is zero between any pairs which do not share a common stock.
Show 2 more
- Baseline portfolio selects exactly 250 pairs based on p‑values. model
Source sentence
For the baseline portfolio we assume 250 pairs are selected for trading based on their p-values.
- Matching portfolio has m1 = m2 = 0 (no shared‑stock pairs). model
Source sentence
The matching portfolio has m1 = m2 = 0 and the baseline portfolio has m1 = 0.
Data
2017 – 2023 · S&P 500 stocks · equities
- S&P 500 stock price data market-prices public
Source sentence
We estimated the mean and variance for the daily change in log‑prices of all stocks on the S&P 500 using price data from 2010 to 2023.
- Monthly pair‑selection data (lowest p‑value pairs) market-prices public
Source sentence
We kept the variance for the 250 pairs with the lowest p‑value each month. We then took the median value of this set of variances across all stocks and months in our dataset to obtain σ2.
Costs
Modeled
Annual transaction cost of 1% per stock, i.e., daily fee of 0.00397% applied to gross returns.
Source sentence
We model the annual transaction costs for each stock at 1%, translating to a daily fee of 1%/252 days = 0.00397%, consistent with the findings in SEC (2019).
Finds 5
Sharpe 1.23 (benchmark 0.48)
- The matching‑based strategy achieves a gross Sharpe ratio of 1.23, far above the baseline’s 0.48 and the market’s 0.59. performance
Source sentence
Notably, our matching‑based strategy showcases a marked improvement in risk‑adjusted performance, evidenced by a gross Sharpe ratio of 1.23, a significant enhancement over the baseline value of 0.48 and market value of 0.59.
- Matching portfolios reduce variance by eliminating the covariance term that accounts for about 50% of baseline variance. theoretical
Source sentence
Most of this difference comes from the covariance of the pairs with shared stocks, which represents 50% of the variance in the baseline portfolio. This covariance term does not exist in the matching portfolio, producing a much lower portfolio variance.
- Net returns of matching approaches are positive (~66%) while baseline approaches are negative after transaction costs. performance
Source sentence
Overall, the matching approaches returned near 66%, while the baseline approaches returns -26.15% and -13.40%.
- Matching portfolio turnover is about one‑third of the baseline, leading to lower transaction‑cost drag. performance
Source sentence
The matching method has a median turnover one third as large as the baseline method.
- Matching strategies achieve annualized net returns of ~7.6% with Sharpe ratio 1.23, comparable to the S&P 500’s 10.79% return but with superior risk‑adjusted metrics. performance
Source sentence
The net annualized returns of the matching‑based strategies are 7.64% and 7.25%, slightly below the S&P 500’s value of 10.79%.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 52 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 (40)
- Random Graphs (2001)
- Direct Estimation of Equity Market Impact (2005) — link
- Statistical Arbitrage in the US Equities Market (2010)
- Optimal Portfolio Diversification Using the Maximum Entropy Principle (2008) — link
- Trading strategies with copulas (2013)
- High Frequency Equity Pairs Trading: Transaction Costs, Speed of Execution and Patterns in Returns (2010)
- Selection of a Portfolio of Pairs Based on Cointegration: A Statistical Arbitrage Strategy (2013)
- Maximum drawdown, recovery, and momentum (2021)
and 32 more
- Pairs trading with partial cointegration (2018)
- Quantitative spread trading on crude oil and refined products markets (2012)
- Does Simple Pairs Trading Still Work? (2018)
- Are pairs trading profits robust to trading costs? (2012)
- Linear-time approximation for maximum weight matching (2014)
- Paths, trees, and flowers (1965)
- Pairs Trading (2004)
- Efficient Algorithms for Finding Maximum Matching in Graphs (1986)
- Pairs Trading: Performance of a Relative Value Arbitrage Rule (2006)
- GitHub (2023)
- Idiosyncratic Risk Matters! (2003)
- Active Portfolio Management (2000)
- Low moments for small samples: a comparative study of order statistics (1947)
- Statistical Arbitrage Pairs: Can Cointegration Capture Market Neutral Profits (2013)
- Pairs selection and outranking: An application to the S and P 100 index (2009)
- Pairs trading and selection methods: is cointegration superior? (2015)
- Étude comparative de la distribution florale dans une portion des Alpes et des Jura (1901)
- Dynamic Portfolio Selection in Arbitrage (2007)
- An entropy-based approach to portfolio optimization (2020)
- Testing the null hypothesis of stationarity against the alternative of a unit root (1992)
- Advanced Engineering Mathematics (1979)
- The Principles of Quantum Mechanics (1981)
- Pairs trading: A copula approach (2013)
- Optimal Convergence Trade Strategies (2012)
- Testing for a Unit Root in Time Series Regression (1988)
- How Fees and Expenses Affect Your Investment Portfolio (2019) — link
- The sharpe ratio, the journal of portfolio management (1994)
- Performance measurement in a downside risk framework (1994)
- SPGlobal (2020)
- Pairs Trading, Quantitative Methods and Analysis (2004)
- Cointegration and Error-Correction Models (2004)
- Yahoo Finance (2023)
0 of 40 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.