Paper: arXiv 2412.14361

Authors: Alessandro Massaad, Rene Moawad, Oumaima Nijad Fares, Sahaphon Vairungroj

Abstract

We revisit the long-only trend-following strategy presented in A Century of Profitable Industry Trends by Zarattini and Antonacci, which achieved exceptional historical performance with an 18.2% annualized return and a Sharpe Ratio of 1.39. While the results outperformed benchmarks, practical implementation raises concerns about robustness and evolving market conditions. This study explores modifications addressing reliance on T-bills, alternative fallback allocations, and industry exclusions. Despite attempts to enhance adaptability through momentum signals, parameter optimization, and Walk-Forward Analysis, results reveal persistent challenges. The results highlight challenges in adapting historical strategies to modern markets and offer insights for future trend-following frameworks.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 8.0)

Why this score: The paper involves advanced mathematical modeling with formal definitions of indicators (Keltner/Donchian channels, volatility scaling) and empirical testing using multiple data splits, point-in-time compliance, and robust validation techniques like Walk-Forward Analysis.

Research Flowchart

  flowchart TD
  Goal["Research Goal: Test Robustness of<br>100-Year Industry Trend Strategy"] --> Inputs
  subgraph Inputs ["Data Inputs"]
      I1["Historical Industry Returns"]
      I2["Treasury Bill Data"]
  end
  Inputs --> Method
  subgraph Method ["Key Methodology"]
      M1["Long-Only Trend Following"]
      M2["Walk-Forward Analysis"]
      M3["Parameter Optimization"]
  end
  Method --> Comp
  subgraph Comp ["Computational Processes"]
      C1["Simulate Strategy &<br>Calculate Metrics"]
      C2["Analyze Drawdowns<br>& Risk"]
      C3["Test Adaptations<br>excl. T-Bills"]
  end
  Comp --> Find
  subgraph Find ["Key Findings & Outcomes"]
      F1["Challenge: Declining<br>Performance in Modern Markets"]
      F2["Issue: Reliance on<br>Safe-Haven Assets"]
      F3["Outcome: Framework for<br>Future Robustness Testing"]
  end

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 modifications to the original long‑only industry trend‑following strategy, addressing reliance on T‑bills, introducing alternative fallback allocations, and exploring industry exclusions.

Source sentence
This study explores modifications addressing reliance on T-bills, alternative fallback allocations, and industry exclusions.

Assumes 5

  • The strategy uses T‑bills as the default risk‑free allocation. market
    Source sentence
    First, The reliance on T-bills as the default risk-free allocation poses practical challenges for real‑world application
  • Point‑in‑time compliance is maintained, i.e., no future information is used. data
    Source sentence
    Point-in-time (PIT) compliance is rigorously maintained throughout the analysis to ensure that no future information is used in decision‑making.
  • Rolling periods and volatility targets are optimized on in‑sample data and assumed to improve out‑of‑sample performance. model
    Source sentence
    Using an in‑sample dataset, we optimized these parameters to maximize performance metrics such as the Sharpe
  • Industry portfolios are rebalanced annually based on market capitalization and SIC codes. data
    Source sentence
    Each industry portfolio is rebalanced annually based on market capitalization, ensuring representative and dynamic weighting over time.
Show 1 more
  • Transaction costs are not explicitly modeled in the reported results. execution
    Source sentence
    Short rolling periods improve sensitivity to price movements, enabling faster trend detection but increasing turnover, noise, and transaction costs.

Data

Backtest sample: 1926 – 2024 · U.S. industry portfolios · equities · daily

  • 48 Industry Portfolios · Kenneth French’s Data Library market-prices public
    2000–2024 · 48 U.S. industry portfolios
    Source sentence
    The industry portfolio return database is constructed using data sourced from Kenneth French’s online data library
  • Fama‑French Research Factors · Kenneth French’s Data Library market-prices public
    2000–2024
    Source sentence
    The dataset includes daily market risk factors, such as the combined market return and risk‑free Treasury bill (T‑bill) rates.

Recognised sources: CRSP Kenneth French Data Library

Costs

Not modeled A trading or execution result is reported without costs.

Finds 5

Reported performance (Long-only industry momentum trend-following): Sharpe 1.39 (benchmark 0.63) · annual return 18.2%

  • The original strategy reported an average annual return of 18.2% with a Sharpe Ratio of 1.39, outperforming the U.S. equity market’s 9.7% return and 0.63 Sharpe Ratio. performance
    Source sentence
    reporting an average annual return of 18.2% with a Sharpe Ratio of 1.39, outperforming the U.S. equity market’s 9.7% return and 0.63 Sharpe Ratio
  • The moving‑average‑based fallback emerged as the most effective mechanism for maintaining capital allocation. performance
    Source sentence
    The moving-average-based fallback emerged as the most effective mechanism for maintaining capital allocation.
  • A momentum signal reduced reliance on fallback methods but still faced challenges in generalizing across live trading periods. performance
    Source sentence
    A momentum signal reduced reliance on fallback methods but still faced challenges in generalizing across live trading periods.
  • Equal‑weight allocation and S&P 500 fallback approaches improved capital deployment but lacked robustness in out‑of‑sample validation. performance
    Source sentence
    Equal-weight allocation and S&P 500 fallback approaches improved capital deployment but lacked robustness in out-of-sample validation.
  • Industry exclusion provided performance enhancements in‑sample but failed to generalize effectively out‑of‑sample. performance
    Source sentence
    Industry exclusion provided performance enhancements in-sample but failed to generalize effectively.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 35 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 1 paper in the archive (1 by independent authors)

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 (10)

  1. A Century of Profitable Industry Trends (2024)
  2. 48 Industry Portfolios - Daily (2024)
  3. Fama-French Research Data Factors - Daily (2024)
  4. Walk Forward Testing Explained in Simple Terms (2024)
  5. Google Colab Notebook: Reworked Strategy with Momentum (2024)
  6. Google Colab Notebook: Final Moving Average Fallback Method Code (2024)
  7. Google Colab Notebook: Final Risk-Parity Fallback (2024)
  8. Google Colab Notebook: Final Equal Weight Fallback (2024)
and 2 more
  1. Google Colab Notebook: Optimizations (2024)
  2. Wall-Forward Analysis Implementation (2024)

0 of 10 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.