Grid
Evaluate the configured combinations of parameter values. Useful when the search space is small enough to examine systematically.
Code → Backtest → Research → Order. In the Research stage, separate parameter decisions made using earlier data from evaluation on later data. Studio keeps that sequence visible, configurable, and reproducible.
Define the strategy, parameters, costs, and search method. Use the training window to select the configuration.
Examine the chosen setup on a later period. Keep this evaluation separate from the training result.
Reserve another chronological period for out-of-sample (OOS) assessment. Changes made after inspecting it should be treated as new research decisions.
The search method changes how candidate parameters are explored. It does not remove the need for independent evaluation.
Evaluate the configured combinations of parameter values. Useful when the search space is small enough to examine systematically.
Leave parameters unchecked to hold them constant. Compare a controlled configuration with the same data, costs and date interval.
Use population-based selection and variation to search the parameter space. Treat the selected configuration as a candidate that still needs validation.
Genetic is the default search method. Keep the seed, bounds and budget with the result; the search objective is terminal net profit, with other metrics reviewed separately.
Plan successive training and evaluation windows before running. Studio supports editable rolling or expanding research folds so you can examine a selection process as the available history advances.
Rolling windows move the training period forward. Anchored windows keep its starting point fixed while the training history grows.
Read the research setup guideA walk-forward study repeats a chronological process. Interpret it as a series of linked experiments, with the window definitions, optimization choices, and assumptions preserved.
The diagram explains time order. It does not represent a completed study or a performance claim.
Results brings equity, drawdown, daily Sharpe, trial and fold outcomes, and per-fill Trade History into one workspace. Retain the run receipt and inspect the exact source, inputs and execution settings.
A backtest is an experiment on selected history under specified rules. Source coverage, quote construction, corporate actions, costs, and information availability can all change its meaning.
Historical results do not establish future returns. The purpose of this workspace is to make the experiment easier to examine and repeat.
Review data and timing assumptionsGet to know the workflow before you begin.