Factor Research Workflow

Testing one factor on one period and deploying is data mining. Systematic factor research requires IC significance, stability across subperiods, decay profiling, and capacity estimation before any factor enters a model.

The Problem

A researcher computes 12-month momentum, sees rank IC of 0.04, and adds it to the model. Six months later the factor collapses because the original test never checked significance, stability, decay, or capacity.

The Pattern

WRONG

# Test one factor, one period, deploy on a single positive number
from scipy.stats import spearmanr

factor = prices.pct_change(252)  # 12-month momentum
fwd_ret = prices.pct_change(21).shift(-21)  # 1-month forward return