Write a testable algorithmic-trading hypothesis with an explicit plan, test, review, and action rule.
Principle: the hypothesis is the unit of learning, not the equity curve. Plan the claim State the market behavior you believe exists, the reason it should exist, and the data that would count as evidence. In trading, vague goals like find momentum or improve Sharpe invite silent curve fitting. A plan says exactly what the signal is expected to do and what would falsify it. Do the smallest honest test Run the first test with conservative assumptions: realistic fees, slippage, borrow constraints if relevant, and a sample split that was not chosen after seeing results. The goal is not to…
Sign up free — one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in