Strategy Development Workflow

Strategies fail because developers skip straight to modeling. The correct process spends most time on hypothesis and data, with modeling as a small fraction.

The Problem

A researcher downloads data, fits a model, runs a backtest, and sees a 2.5 Sharpe ratio. They deploy, then lose money because there was no documented hypothesis, no feature validation, no cost model, and no holdout.

The Pattern

WRONG

# Jump straight to modeling - no hypothesis, no validation gates
import lightgbm as lgb