Paper: arXiv 2404.18017

Authors: Prabhu Prasad Panda, Maysam Khodayari Gharanchaei, Xilin Chen, Haoshu Lyu

Abstract

The paper examines the performance of regression models (OLS linear regression, Ridge regression, Random Forest, and Fully-connected Neural Network) on the prediction of CMA (Conservative Minus Aggressive) factor premium and the performance of factor timing investment with them. Out-of-sample R-squared shows that more flexible models have better performance in explaining the variance in factor premium of the unseen period, and the back testing affirms that the factor timing based on more flexible models tends to over perform the ones with linear models. However, for flexible models like neural networks, the optimal weights based on their prediction tend to be unstable, which can lead to high transaction costs and market impacts. We verify that tilting down the rebalance frequency according to the historical optimal rebalancing scheme can help reduce the transaction costs.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper employs standard regression models and portfolio optimization formulas rather than advanced derivations, placing it at a moderate math level. It demonstrates strong empirical rigor with detailed backtesting on 60 years of data, out-of-sample validation, transaction cost modeling, and sensitivity analysis on rebalancing frequency.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Optimize Factor Timing for CMA"] --> B["Model Selection & Data"]
  B --> C["Prediction Phase<br>(Out-of-Sample R²)"]
  B --> D["Backtesting Phase<br>(Investment Performance)"]
  
  subgraph B
      direction LR
      B1["Inputs<br>Historical CMA Premium"]
      B2["Models<br>OLS, Ridge, RF, NN"]
      B1 & B2
  end
  
  C --> E["Key Finding 1<br>Flexible Models (RF/NN) > Linear Models"]
  D --> F["Key Finding 2<br>Flexible Models Overperform<br>but High Transaction Costs"]
  
  E & F --> G["Optimization<br>Adaptive Rebalancing Frequency"]
  G --> H["Final Outcome<br>Cost-Efficient Factor Timing"]

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 evaluates regression models for predicting the CMA factor premium and uses them for factor‑timing investment strategies.

Source sentence
The paper examines the performance of regression models (OLS linear regression, Ridge regression, Random Forest, and Fully-connected Neural Network) on the prediction of CMA (Conservative Minus Aggressive) factor premium and the performance of factor timing investment with them.

Assumes 6

  • Investors are risk‑averse and maximize a mean‑variance utility. model
    Source sentence
    We assume a risk averse (Sharpe, 1964) and (Welch and Goyal, 2008) utility function 𝐸[𝑟] − 𝛾. 𝜎𝑟2 (Shanken and Weinstein, 1990)
  • The portfolio consists of only the CMA factor and a risk‑free asset. market
    Source sentence
    The research focuses on a two-asset portfolio between CMA factor and risk-free asset (Shanken, 1982) and (Shanken and Weinstein, 1990).
  • Optimal weight is computed as 1/γ times expected return over variance. model
    Source sentence
    the optimal weight (Welch and Goyal, 2008) in the factor that can maximize the utility: 𝜔𝑡∗= 1/𝛾 . 𝐸[𝑟𝑡+1]/𝜎𝑟2 = 1/𝛾 . 𝑓(𝑿𝑡)/𝜎𝑟2
  • Transaction cost is proportional to the change in position (basis points per trade). execution
    Source sentence
    In this session, we assume that the transaction cost is proportional to the change in position.
Show 2 more
  • When modeling quadratic costs, they are equivalent to linear market impact. execution
    Source sentence
    If we assume that the transaction cost is quadratic to the change in position, which is equivalent to linear market impact assumption.
  • Training uses an expanding window; NN3 is trained on the initial training period only to avoid over‑fitting. model
    Source sentence
    NN3 is trained on the training only without expanding window to avoid overfitting (Merton, 1980) and handle computational complexity

Data

  • Fama‑French factor data · Kenneth French’s data library macro public
    January 1963 to December 2022
    Source sentence
    We source our factor data from Fama and French (Breeden, 1979), accessible at Kenneth French’s data library (Breeden et al., 1989) (monthly, January 1963 to December 2022)
  • Welch and Goyal timing variables · Goyal’s website macro public
    January 1871 to December 2022
    Source sentence
    our timing variable data from Welch and Goyal (2008), accessible at Goyal’s website (Campbell and Thompson, 2008) (monthly, January 1871 to December 2022)

Recognised sources: Kenneth French Data Library

Costs

Modeled Costs are part of the reported headline results.

Proportional costs of 10‑50 basis points are applied; quadratic cost of 20‑50 bps is also examined.

Source sentence
Starting from proportional transaction cost is 20bps, all models will underperform the constant weighting scheme. If the proportional transaction cost is 50bps, all models will underperform the constant weighting scheme.

Finds 5

  • More flexible models (NN3 and random forest) achieve higher out‑of‑sample R‑squared in predicting the CMA premium. predictive-accuracy
    Source sentence
    The outcome shows that more flexible structures like NN3 and random forest can better explain the variance in the factor premium of the unseen period.
  • Factor‑timing with random forest yields stable out‑of‑sample wealth growth, the highest Sharpe ratio, and lower downside risk than NN3. performance
    Source sentence
    According to the wealth paths, factor timing with the random forest provides a stably better performance than both linear candidates and the unconditional optimal weighting, and it entails much lower downside risk than NN3. Among all strategies of factor timing, random forest often yields the highest Sharpe Ratio.
  • NN3’s optimal weights fluctuate heavily, leading to large return erosion when transaction costs are considered. performance
    Source sentence
    However, the optimal weights defined with NN3 obviously fluctuates much more fiercely than other models, which can lead to much larger erosion if transaction cost is considered.
  • When proportional transaction costs are low (e.g., 10 bps) monthly rebalancing and optimal‑interval rebalancing perform similarly; at higher costs (50 bps) optimal rebalancing adds extra return (0.13 % for random forest, 0.63 % for NN3). performance
    Source sentence
    For instance, if there exists a proportional transaction cost of 50bps, the optimal rebalancing interval for the factor timing with random forest and NN3 can lead to an annualized 0.13% and 0.63% of extra return on the latter 60% of the OOS months.
  • Ridge regression produces weights similar to OLS under Campbell‑Thompson restrictions but incurs higher turnover and transaction costs. performance
    Source sentence
    ridge (L2‑regulated) linear regression provides very similar wealth path as the OLS linear regression under Campbell and Thompson restrictions. However, factor timing with ridge will entail a slightly larger position changes than OLS, which can lead to larger erosion if transaction cost is considered.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 33 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.