Paper: arXiv 2412.12350
Authors: Georgios M. Gkolemis, Adwin Richie Lee, Amine Roudani
Abstract
This report presents a systematic market-neutral, multi-factor investment strategy for New York Stock Exchange equities with the objective of delivering steady returns while minimizing correlation with the market. A robust feature set is integrated combining momentum-based indicators, fundamental factors, and analyst recommendations. Using various statistical tests for feature selection, the strategy identifies key drivers of equity performance and ranks stocks to build a balanced portfolio of long and short positions. Portfolio construction methods, including equally weighted, risk parity, and minimum variance beta-neutral approaches, were evaluated through rigorous backtesting. Risk parity demonstrated superior performance with a higher Sharpe ratio, lower beta, and smaller maximum drawdown compared to the Standard and Poor’s 500 index. Risk parity’s market neutrality, combined with its ability to maintain steady returns and mitigate large drawdowns, makes it a suitable approach for managing significant capital in equity markets.
Complexity vs Empirical Score
- Math Complexity: 6.0/10
- Empirical Rigor: 6.0/10 (capped from 8.5: transaction costs not modelled; see penalty flags)
- Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 8.5)
Why this score: The paper applies advanced statistical methods (Lasso regression, multivariate regression) and mathematical formulations for feature engineering (e.g., trended momentum via linear regression), but is heavily grounded in real-world implementation with detailed data sourcing, Point-in-Time constraints, and rigorous multi-period backtesting.
Research Flowchart
flowchart TD A["Research Goal:<br>Create a market-neutral, multi-factor<br>NYE equity strategy"] --> B["Input: Feature Set<br>Momentum, Fundamental, Analyst"] B --> C["Computational Process:<br>Statistical Feature Selection"] C --> D["Computational Process:<br>Portfolio Construction & Backtesting<br>Equally Weighted, Risk Parity, Min Variance"] D --> E["Key Outcome:<br>Risk Parity Outperforms<br>Higher Sharpe, Lower Beta, Low Drawdown"]
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 systematic market‑neutral, multi‑factor investment strategy for NYSE equities using risk‑parity portfolio construction.
Source sentence
This report presents a systematic market-neutral, multi-factor investment strategy for New York Stock Exchange equities with the objective of delivering steady returns while minimizing correlation with the market.
Assumes 5
- Data are point‑in‑time to avoid look‑ahead bias. data
Source sentence
Within each sample, we ensured that the data remained Point-In-Time (PIT). When a dataset is characterized as PIT, each data point only contains information that would have been available at the respective date
- No leakage between in‑sample and out‑of‑sample data. data
Source sentence
Precautions were taken to avoid leakage between in-sample and out-of-sample data.
- Trades are executed monthly and held for one month. execution
Source sentence
... This position will be held for a month before we repeat this same process.
- Long and short positions are formed from the top and bottom 40 stocks respectively. execution
Source sentence
bottom 40 are chosen to be shorted.
Show 1 more
- Risk parity portfolio is market‑neutral (beta ≈ 0). model
Source sentence
Both portfolios are observed to be market neutral.
Data
2016 – 2024 · NYSE equities · equities · monthly
- NYSE daily equity prices market-prices commercial
Source sentence
... were extracted from the Wharton Research Data Services (WRDS) databases.
- Company monthly fundamental factors fundamentals commercial
Source sentence
company monthly fundamental factors
- Analyst recommendations alternative commercial
Source sentence
analyst recommendations at various frequencies
Costs
Not modeled
Finds 1
Sharpe 0.89 (benchmark 0.80) · max drawdown 8.8%
- Risk parity portfolio achieved the highest Sharpe ratio (0.89 validation, 0.81 out‑of‑sample) with beta near zero and lower maximum drawdown than the S&P 500. performance
Source sentence
Since risk parity achieved the highest Sharpe ratio, lowest absolute value of beta and a small maximum drawdown, it was selected as the preferred portfolio construction method for our strategy.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 3 related papers). Coverage is partial, so this is neither replication nor refutation.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (8)
- About CGS Identifiers (2024) — link
- The relative strength index revisited (2011)
- Momentum, direction, and divergence (1995)
- Trended Momentum (2024)
- The characteristics of factor investing (2019)
- Multifactor portfolio efficiency and multifactor asset pricing (1996)
- Multifactor asset pricing analysis of international value investment strategies (1998)
- A Fast Algorithm for Computing High-Dimensional Risk Parity Portfolios (2013)
0 of 8 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.