Trading strategy backtester
Finisdom’s Strategy Lab runs SMA crossovers, momentum, breakouts, RSI and MACD rules through walk-forward, out-of-sample testing — not to crown a winner, but to show honestly which edges hold up and which were just curve-fit luck.
What it does
- A library of rule strategies (SMA cross, momentum, breakout, RSI, MACD)
- In-sample vs out-of-sample split — ranked on data the rule wasn’t tuned on
- A six-filter robustness gauntlet, each shown pass/fail
- A permutation “skill vs luck” p-value on every strategy
- Long/flat and strictly causal — the signal sets the next day’s position, no lookahead
- Per-market-regime breakdown so you see where an edge actually lives
How it works
Pick an instrument
Choose any instrument with a couple of years of history — the funnel needs enough out-of-sample data to be meaningful.
Run the funnel
Every rule is backtested out-of-sample, put through six robustness filters, and stress-tested with a permutation test that shuffles returns to estimate luck.
Read the survivors
Strategies are ranked by out-of-sample Sharpe, survivors first. For most instruments few or none survive — which is exactly the honest result.
Frequently asked
What is a trading strategy backtester?
A strategy backtester replays a trading rule over historical prices to estimate how it would have performed. The hard part isn’t running one backtest — it’s telling a real edge from an overfit one, which is why Finisdom wraps every rule in out-of-sample validation and a luck test rather than reporting a single flattering curve.
What is walk-forward / out-of-sample testing?
The strategy is judged on data it wasn’t chosen on: history is split into an in-sample “discovery” window and a later out-of-sample window, and all ranking uses the out-of-sample result. Walk-forward extends this across rolling folds so an edge has to hold up in period after period, not just once.
How do you tell skill from luck?
A permutation test shuffles the instrument’s returns to destroy any real structure, re-runs the same rule, and builds a distribution of “lucky” Sharpe ratios. The p-value is how often luck matched the real result — a low value means the edge is unlikely to be chance.
Why do so few strategies survive?
Because most rule strategies are curve-fit to past noise. Test enough of them and one will look brilliant by accident. The funnel’s job is to expose that — on a strong trending index, for example, no timing rule may beat simply buying and holding, and the tool says so plainly.
Is the Strategy Lab free?
The Strategy Lab is part of the Finisdom cockpit, available to members. The Learn section explains out-of-sample testing and why backtests lie, in plain English, for free.
More Finisdom tools
Backtest any multi-asset portfolio against decades of real history — Sharpe, Sortino, Calmar, max drawdown, rolling returns, and crash stress tests, benchmarked and split by bull and bear regimes.
Trace the efficient frontier for any set of assets and compare max-Sharpe, min-volatility, equal-weight, inverse-vol, and risk-parity allocations — with honest walk-forward validation, not a curve fit.
Decompose any portfolio’s return against its benchmark — allocation, selection, and interaction effects — with factor-risk exposures, tracking error, information ratio, and marginal contribution to risk (MCTR).
A single 0–100 read on whether the market backdrop favours deploying capital or holding back — built from trend, credit, volatility, and breadth signals, with an S&P 500 deployment-zone overlay.
Pair a disciplined quant signal with a Claude fundamental-quality review, blended into one verdict — momentum, value, and quality scored by the engine, business durability read by the model.
Real-money implied probabilities from Kalshi prediction markets for the Fed, inflation, recession, and GDP — plus a Claude-written weekly brief that reads the whole macro picture in plain English.
Track a dozen economically-linked pairs — gold vs real yields, credit vs stocks, the 60/40 hedge — and see which have pulled apart from their own norm, each with the historical base rates of what followed.
What actually happened after past earnings surprises: every reported quarter since 2008 pooled and bucketed by surprise size, with the forward drift at 5, 21, and 63 sessions and the sample size on every number.
Ten concentrated, actively-managed funds — their largest positions, what they opened, exited, added and trimmed last quarter, and where any of it overlaps your own book. Index giants deliberately excluded.
Design a fund as a rule rather than a basket, replay it point-in-time across decades, then freeze it and publish it to a leaderboard that ranks funds on how much of their backtest they actually kept.
Backtests and optimizations are hypothetical illustrations built from historical data — not predictions, and not investment advice. Past performance does not guarantee future results.