SerenQuantDocs
Sign up
Sign up
© 2026 SerenQuant. All rights reserved.
DocsPrivacyTermsStatusSupport
Docs
Documentation
Start here
Overview
Guide library
GuidesGetting Started: APIGetting Started: MCPAuth + Workspace ScopesAccount and Workspace ManagementMarkets WorkspaceMarkets Symbol WorkspaceMarket Guides and Beta ScopeFutures ReadinessResearch WorkflowResearch Workbench, Pipeline, and ExperimentsResearch Specialist MethodsResearch Context SurfacesBacktests Run LifecycleBacktests Run Detail and CompareStrategy Sweeps and OptimizerExecution WorkflowProviders and BenchmarkingSettings and Runtime ConfigAgent WorkbenchNews WorkflowDatasets WorkflowGlobal Language SelectionMFA Getting StartedMFA Recovery + Device LossMFA Trusted DevicesMFA API ReferenceLLM Market Analysis LoopStrategy Generation + Backtest LoopPromotion + Risk Guardrails
Reference
API ReferenceMCP Reference
Lifecycle
Changelog
  1. Docs/
  2. Guides/
  3. Strategy Sweeps and Optimizer
Public docs

Guide: Strategy Sweeps and Optimizer

Use sweep setup, sweep detail, and optimizer surfaces when strategy selection and allocation need deeper tooling.

Deep surface guide

What this guide covers

Use this guide when you need to move from one-off strategy validation into broader parameter search and allocation design across the signed-in strategy tooling.

Sweeps are for parameter search and candidate ranking. Optimizer is for portfolio construction once the candidate universe is clearer.

Treat sweep detail as an evidence surface with leaderboard, Pareto, statistics, and compare actions rather than just a run log.

Keep the handoff into compare, backtests, and allocation explicit so strategy search and position design do not drift apart.

Routes and surfaces

These are the deeper strategy-tooling surfaces behind strategy exploration and allocation design.

/strategies/sweeps · setup, grid, ranking policy

Sweeps setup

Define universe, strategy, parameter grid, density, and ranking policy before you launch a sweep.

/strategies/sweeps · recent runs

Recent sweeps

Review prior sweep runs and reuse their context instead of relaunching without a history check.

/strategies/sweeps/[sweepId]

Sweep detail

Inspect progress, leaderboard, Pareto rows, statistics, memo output, and selected-run comparison for a sweep.

/strategies/optimizer · profiles & constraints

Optimizer profiles

Create and tune allocation profiles, solver settings, and constraint policies before you solve anything.

/strategies/optimizer · solve universe & allocations

Optimizer solve and allocations

Select the universe, seed expected returns, tune bounds, and inspect allocation diagnostics plus result rows.

Recommended strategy-tooling loop

Use this sequence to keep strategy search and allocation design connected but distinct.

01

Define the sweep precisely

Start by fixing the watchlist, instrument, interval, parameter grid, and ranking policy so the search space is explicit.

02

Rank and inspect sweep detail

Use leaderboard, Pareto, statistics, and memo surfaces to understand why the best-looking runs are winning.

03

Compare the strongest candidates

Move selected runs into compare or deeper backtest review before you treat the sweep winner as final.

04

Design the allocation separately

Use optimizer profiles, solver constraints, and allocation diagnostics after the candidate universe is already credible.

Review and guardrails

Do not treat sweep ranking as enough by itself. Use sweep detail and compare to validate why a candidate is winning.

Keep parameter-grid assumptions explicit so later sweeps are comparable rather than cosmetically different.

Use optimizer profiles and bounds as governance controls, not just numeric tuning knobs.

Separate strategy selection from allocation design so a weak strategy is not disguised by a good optimizer outcome.

Next steps

Open Strategy Sweeps

Jump into the sweeps surface to define the search space and inspect recent sweep runs.

Open Optimizer

Open the optimizer when the candidate set is ready for explicit profile, constraint, and allocation design.

Backtests run detail guide

Return to run-detail validation when a sweep winner or optimizer output still needs deeper backtest evidence.

Last updated

Mar 24, 2026

Feedback

Report unclear guidance, stale contracts, missing coverage, or broken docs UI on this page.

Open feedback issue
Previous
Backtests Run Detail and Compare
Next
Execution Workflow
On this page

Jump to the section you need without losing your place.

  • What this guide covers
  • Routes and surfaces
  • Recommended strategy-tooling loop
  • Review and guardrails
  • Next steps
Last updated

Mar 24, 2026

Feedback

Report unclear guidance, stale contracts, missing coverage, or broken docs UI on this page.

Open feedback issue