Backtesting
Testing a trading strategy against historical price data to estimate how it would have performed. Sigmentum's HindsightSandbox runs backtests across 2 years of real data in seconds, free for all accounts.
How Sigmentum uses it
Backtesting answers the question: "if I had applied this rule over the last N years, what would have happened?" It is not a guarantee of future performance — markets change, and a strategy that worked in 2022 may not work in 2026. The most common backtesting errors are: (1) overfitting — tuning parameters until the historical results look good, then finding they do not generalize; (2) survivorship bias — only testing on assets that still exist; (3) not accounting for slippage and spread. Sigmentum's Hindsight Sandbox addresses the latter by applying a realistic fill model.
Every Sigmentum signal shows the exact values — Backtesting and the other three inputs — in the AI reasoning breakdown. Free account, no credit card.
Open Sigmentum free →