Factor Evaluation

A factor that looks predictive may be untradeable due to high turnover, rapid decay, or non-monotonic quantile spreads. Comprehensive evaluation before portfolio integration prevents costly live failures.

The Problem

Reporting a single backtest Sharpe ratio conflates signal quality with portfolio construction. A factor with IC 0.03 and low turnover can be more valuable than one with IC 0.05 and 80% daily turnover - whether IC is sufficient depends on breadth, turnover costs, and regime stability. Without decomposing signal quality into IC, quantile monotonicity, turnover, and decay, you cannot diagnose why a strategy fails or how to improve it.

The Pattern

WRONG

# Evaluate only via backtest Sharpe - hides factor-level issues
returns = run_backtest(signal)
sharpe = returns.mean() / returns.std() * np.sqrt(252)
print(f"Sharpe: {sharpe:.2f}")  # No idea why it works or doesn't

CORRECT