Paper: arXiv 2401.00001

Authors: Runjia Yang, Beining Shi

Abstract

This study presents an analytical approach to sector rotation, leveraging both factor models and fundamental metrics. We initiate with a systematic classification of sectors, followed by an empirical investigation into their returns. Through factor analysis, the paper underscores the significance of momentum and short-term reversion in dictating sectoral shifts. A subsequent in-depth fundamental analysis evaluates metrics such as PE, PB, EV-to-EBITDA, Dividend Yield, among others. Our primary contribution lies in developing a predictive framework based on these fundamental indicators. The constructed models, post rigorous training, exhibit noteworthy predictive capabilities. The findings furnish a nuanced understanding of sector rotation strategies, with implications for asset management and portfolio construction in the financial domain.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 6.0/10 (capped from 6.5: transaction costs not modelled; see penalty flags)
  • Quadrant: Street Traders — empirical and applied, lower math complexity (effective empirical rigor capped from 6.5)

Why this score: The paper applies standard factor models and basic statistical metrics, showing moderate empirical rigor with backtested returns and Sharpe ratios, but uses low-level math without complex derivations.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Develop Predictive Framework<br>for Sector Rotation"] --> B["Data Collection & Classification<br>Sector Returns & Fundamental Metrics"]
  B --> C["Factor Model Analysis<br>Momentum & Short-term Reversion"]
  B --> D["Fundamental Analysis<br>PE, PB, EV/EBITDA, Div Yield"]
  C & D --> E["Computational Process<br>Model Construction & Rigorous Training"]
  E --> F["Key Outcome<br>High Predictive Capability<br>Asset Management Strategy"]

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 predictive framework for sector rotation based on fundamental indicators.

Source sentence
Our primary contribution lies in developing a predictive framework based on these fundamental indicators.

Assumes 3

  • Portfolio is rebalanced on a monthly frequency. execution
    Source sentence
    Then we trade our portfolio under a monthly frequency.
  • Long positions are taken in the two sectors with highest factor exposures and short the two with lowest. execution
    Source sentence
    we rank the factor exposures for each sector and take long positions of sectors with the highest two factor exposures, take short position of sectors with the lowest two factor exposures.
  • Sample size is small, raising over‑fitting concerns for neural‑network models. model
    Source sentence
    Considering our sample size is small, intuitively we need to focus more on the overfitting problem.

Data

  • Quarterly data for 11 indices · Bloomberg fundamentals commercial
    11 sector indices
    Source sentence
    We collected quarterly data for all 11 indices from Bloomberg, including their P/E ratio, EV/EBIT, Profit Margin, etc.
  • Daily sector returns (2002‑2022 February) market-prices unknown
    2002-2022 February · sector level
    Source sentence
    Between 2002 and 2022 February, the results are:

Recognised sources: Bloomberg

Costs

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

Finds 3

  • The MOM 7M factor yields a maximum annual return of 21.19% and a Sharpe ratio of 0.62. performance
    Source sentence
    From this table, we can tell that by using the MOM 7M factor, we can reach a maximum annual return rate of 21.19% and a maximum Sharpe ratio of 0.62.
  • The 30‑day short‑term reversion factor delivers an average annual return of 8.77% with a Sharpe ratio of 0.8735. performance
    Source sentence
    It has an optimal annual return rate of 8.77% on average and leads to a sharp ratio of 0.8735.
  • The neural‑network model achieves a test‑set winning rate of 64% (0.59 for positive predictions, 0.72 for negative). predictive-accuracy
    Source sentence
    On the test set, the score of the model is 0.64, which means the model predicts 64% of the results correctly.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 22 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.