Paper: SSRN 7290621
Authors: Sheimy Paz
Abstract
Zarattini, Aziz, and Barbon (2025) present an intraday momentum strategy for SPY that achieves an annualized return of 19.6% and a Sharpe Ratio of 1.33 over the period 2007-2024. This paper independently replicates their strategy using IQFeed 1-minute data and evaluates its performance on approximately two years of out-of-sample data (May 2024 to March 2026). Our in-sample replication closely matches the original results, confirming the reproducibility of the strategy (Sharpe Ratio 1.34 over 2015-2024). However, out-of-sample performance deteriorates substantially: the strategy achieves a total return of only 9.4% versus 29.5% for a passive buy-and-hold, with a Sharpe Ratio of 0.39. The decline in risk-adjusted returns is statistically significant. We examine potential explanations for this degradation, including changing market microstructure, the proliferation of zero-days-to-expiration (0-DTE) options, and the possibility that the observed underperformance falls within historical drawdown norms. Our findings highlight the importance of out-of-sample validation for intraday trading strategies and contribute to the ongoing discussion about the persistence of momentum anomalies at high frequencies.
Complexity vs Empirical Score
- Math Complexity: 5.0/10
- Empirical Rigor: 9.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
- Basis: provisional. Scored from the abstract alone because the full text was not available, so both scores reflect what the abstract claims, not a reading of the paper.
Why this score: This paper demonstrates strong empirical rigor through independent replication and extensive out-of-sample validation, which is crucial for intraday strategies. Its novelty lies in the critical re-evaluation of a published strategy and the investigation of performance degradation factors. The methodology is clear and the results are highly reproducible.
Research Flowchart
flowchart TD
A["Research Goal: Replicate & Out-of-Sample Validate Intraday Momentum Strategy"] --> B{"Methodology: Independent Replication & Out-of-Sample Evaluation"};
B --> C["Data: IQFeed 1-Min SPY Data (2007-2026)"];
C --> D{"Computational Process: Strategy Implementation & Performance Metrics (Returns, Sharpe)"};
D --> E["Outcome 1: In-Sample Replication Confirmed (Sharpe 1.34)"];
D --> F["Outcome 2: Out-of-Sample Deterioration (Total Return 9.4%, Sharpe 0.39)"];
F --> G["Analysis: Examine Degradation Causes (Market Microstructure, 0-DTE, Drawdowns)"];
G --> H["Conclusion: Highlights Importance of OOS Validation & Persistence of Momentum Anomaly Debate"];
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 an intraday momentum strategy for the S&P 500 ETF (SPY) and evaluates its performance out-of-sample.
Source sentence
Zarattini, Aziz, and Barbon (2025) present an intraday momentum strategy for SPY that achieves an annualized return of 19.6% and a Sharpe Ratio of 1.33 over the period 2007-2024. This paper independently replicates their strategy using IQFeed 1-minute data and evaluates its performance on approximately two years of out-of-sample data (May 2024 to March 2026).
Assumes
No explicit assumptions found in the text.
Data
2007 – 2024 · S&P 500 ETF (SPY) · equities · intraday
- IQFeed 1-minute data market-prices commercial
Source sentence
This paper independently replicates their strategy using IQFeed 1-minute data and evaluates its performance on approximately two years of out-of-sample data (May 2024 to March 2026).
Costs
Unclear
Finds 4
Sharpe 1.34 · annual return 19.6% · total return 9.4%
- Out-of-sample performance deteriorates substantially, achieving a total return of 9.4% versus 29.5% for a passive buy-and-hold, with a Sharpe Ratio of 0.39. performance
Source sentence
However, out-of-sample performance deteriorates substantially: the strategy achieves a total return of only 9.4% versus 29.5% for a passive buy-and-hold, with a Sharpe Ratio of 0.39.
- In-sample replication closely matches the original results, confirming reproducibility with a Sharpe Ratio of 1.34 over 2015-2024. performance
Source sentence
Our in-sample replication closely matches the original results, confirming the reproducibility of the strategy (Sharpe Ratio 1.34 over 2015-2024).
- The decline in risk-adjusted returns is statistically significant. statistical
Source sentence
The decline in risk-adjusted returns is statistically significant.
- The original intraday momentum strategy achieves an annualized return of 19.6% and a Sharpe Ratio of 1.33 over 2007-2024. performance
Source sentence
Zarattini, Aziz, and Barbon (2025) present an intraday momentum strategy for SPY that achieves an annualized return of 19.6% and a Sharpe Ratio of 1.33 over the period 2007-2024.
Checked by others
Supported by
- Beat the Market An Effective Intraday Momentum Strategy for S&P500 ETF (SPY)
Compare the findings
This paper: The original intraday momentum strategy achieves an annualized return of 19.6% and a Sharpe Ratio of 1.33 over 2007-2024.
That paper: From 2007 to early 2024 the intraday momentum portfolio achieved a total return of 1,985% (net of costs), an annualized return of 19.6%, and a Sharpe Ratio of 1.33.
- "Beat the Market" Revisited An Independent Replication and Statistical Audit of an Intraday Momentum Strategy
Compare the findings
This paper: In-sample replication closely matches the original results, confirming reproducibility with a Sharpe Ratio of 1.34 over 2015-2024.
That paper: Independent replication reproduces almost exactly a total return of 1,989% and Sharpe Ratio of 1.317 on the original window.
- Market Intraday Momentum
Compare the findings
This paper: The original intraday momentum strategy achieves an annualized return of 19.6% and a Sharpe Ratio of 1.33 over 2007-2024.
That paper: The intraday momentum pattern is also present for ten other most actively traded domestic and international ETFs.
Code
No repository by the authors found in the paper.
Extracted 2026-11-15 · same card as JSON · A language model chose these items: check the source sentence before relying on one.