Strategy Builder
Preset
Asset
Costs on. Turning these off is how strategies lie to you.
0.05 1
1 3
Everything this Space has computedCATALOG · PRECOMPUTED FROM THE SIGNAL STORE
Rank by
5 50
0 100
Returns over timeTOP RANKED · CUMULATIVE, COSTS INCLUDED
Risk vs returnMARKER AREA = TRADE COUNT
Best result per modelACROSS EVERY STRATEGY AND ASSET
Asset
every model's latest stored forecast for this slice · weighted by realised accuracy
session runs and runs saved to the signal store
◴
No run loaded
Configure a strategy on the left, or start from a worked example and edit it.
RUN BACKTESTCOSTS DEFAULT ONFILLS AT NEXT BAR OPEN
Run a backtest to generate the report.
Extend coverageRUNS ON YOUR OWN GPU QUOTA
Model
Asset
Timeframe
Add model
Adapter family
Run Manager
no runs yet in this session
SHARPE
Annualized mean excess return divided by return volatility. Above 1 is good; above 3 usually means a bug.
SORTINO
Sharpe with only downside deviation in the denominator.
MAX DRAWDOWN
Worst peak-to-trough decline of the equity curve.
PROFIT FACTOR
Gross profit over gross loss. Below 1.2 rarely survives real costs.
R-MULTIPLE
Trade P&L expressed in units of initial risk.
MAE / MFE
Worst and best unrealized excursion while the trade was open.
WALK-FORWARD
Train on a rolling window, test on the next unseen window, repeat.
OOS
Out of sample: data the parameters never saw during fitting.
BASELINE
A naive forecast (random walk, drift, seasonal). If a learned model cannot beat these, it has not earned its inference cost.
- Fills execute at the next bar's open. A decision at bar
tcan never trade at bart. - Strategies are checked for lookahead by perturbing future prices up and down and asserting past outputs do not move.
- Costs are on by default: commission per side plus a slippage model, both
booked onto every trade row.
gross − costs = netholds exactly. - The locked holdout is excluded from every parameter-selection path, not merely reported separately.
- The store holds raw model outputs only. Trading rules are applied live, per run.
- Catalog rows all use one canonical config (costs on, walk-forward 12/3/3, 6-month holdout) so they are comparable with each other.
Backtested results are hypothetical, derived from historical data, and are not indicative of future results. Nothing here is investment advice. The Bit Trading Company is not a licensed investment adviser.
BITTRADING BACKTEST LAB v1.1.0