Factor Exposure Analysis AI Prompt

Analyze the factor exposures of this portfolio or asset using standard risk factor models.

Portfolio / asset: {{portfolio}}
Factor model: {{factor_model}} (Fama-French 3, Fama-French 5, Carhart 4, Barra, or custom factors)
Time period: {{period}}

1. Factor model regression:
   Run OLS regression of excess returns on factor returns:
   R_i - R_f = α + β₁F₁ + β₂F₂ + ... + βₙFₙ + ε

   For Fama-French 3-factor:
   R_i - R_f = α + β_MKT(R_M - R_f) + β_SMB(SMB) + β_HML(HML) + ε

   Report for each factor:
   - Beta (exposure): with 95% confidence interval
   - t-statistic and p-value
   - Economic significance: what does a 1-unit factor shock imply for portfolio return?

2. Alpha (Jensen's alpha):
   - Report α with standard error and t-statistic
   - Annualized alpha = daily_alpha × 252
   - Is alpha statistically significant (t > 2.0)? Is it economically meaningful?
   - Caveat: alpha depends heavily on which factors are included in the model

3. Model fit:
   - R² and Adjusted R²: what % of return variation is explained by the factors?
   - Information ratio: α / tracking_error (annualized)
   - Residual autocorrelation: Durbin-Watson test on residuals

4. Rolling factor exposures:
   - 252-day rolling betas for each factor
   - Plot over time: are exposures stable or do they drift significantly?
   - Significant beta drift may indicate strategy drift, market regime change, or reconstitution

5. Factor contribution to return:
   - Decompose total return into: factor contribution + alpha + unexplained
   - Factor contribution_i = β_i × Factor_return_i
   - Which factors contributed most positively and negatively over the period?

6. Residual analysis:
   - Is the idiosyncratic risk (residual std) large relative to systematic risk?
   - High idiosyncratic risk suggests security-specific risks not captured by the factor model

Return: factor exposure table with CIs, alpha analysis, R², rolling beta plots, return decomposition, and residual analysis.