⚠ INTERNAL — Operator UX mock · Design preview of V2 development path · demo-wired ≠ production-live · back to dev guide
Polygon · pUSD 10
📓 Developer Guide 📋 Reason Codes 📈 Shadow Mode
JD John Doe · Admin

ModelDriftMonitor

risk.modeldriftmonitor
Risk Guardrail planned Planned frozen flagship

ModelDriftMonitor flags strategies whose live behaviour has decoupled from their backtest distribution.

What it does

ModelDriftMonitor flags strategies whose live behaviour has decoupled from their backtest distribution. It computes a drift score by comparing the rolling distribution of live signals or fill prices against the expected backtest baseline and hard-rejects new orders when drift exceeds the configured ceiling, preventing a degraded model from continuing to place orders.

Pipeline placement

runs after: Strategy OrderIntent ModelDriftMonitor runs before: ExecutionPlan emit

Applies to: Every OrderIntent from a model-driven strategy — detects when live strategy behaviour has drifted from the backtest dist

Why it matters

If this failsConsequence
Model degradation undetectedA strategy whose signal quality has degraded continues placing orders, accumulating losses without any automated circuit-breaker.
Market regime changeA model trained on one market regime may produce pathological signals in a new regime; model drift detection provides an early-warning gate before significant capital is deployed.

Inputs

Polymarket inputs

InputSourceRequiredUse
Recent fill prices and strategy signal valuesclob_authrequiredCompute rolling live distribution for comparison against backtest baseline.
Market metadata (category, volume, resolution type)gammaoptionalProvide context for regime classification to distinguish genuine drift from expected regime variation.

Internal inputs

InputSourceRequiredUse
Strategy backtest distribution summary (mean, std, percentiles)internalrequiredDefine the expected baseline distribution against which live behaviour is compared.
KillSwitch active flagKillSwitchrequiredIf active, reject immediately.

Authority

What this bot is permitted to do

Veto

State

Readiness

Planned

Status

planned

Class

Guardrail

Default mode

planned

Developer owner

Polytraders core — Risk pod

Capital impact

Direct

Reason codes emitted

CodeSeverityMeaningAction
KILL_SWITCH_ACTIVEHARD_REJECTGlobal kill switch active.Immediate HARD_REJECT.
MODEL_DRIFT_EXCEEDEDHARD_REJECTStrategy drift score exceeds the hard ceiling.HARD_REJECT; log drift_score, strategy_id, and metric.
MODEL_DRIFT_WARNWARNDrift score is between warning and hard thresholds.Attach WARN annotation; APPROVE.
MODEL_DRIFT_DATA_UNAVAILABLEHARD_REJECTBacktest baseline unavailable for this strategy.HARD_REJECT (fail-closed).

Used by

Reverse index — strategies that currently reference risk.modeldriftmonitor. If you change this bot's authority or reason codes, these strategies must re-pass shadow.

StrategyStateActivity
BTC weekly — close-aware quotesdemo-wiredlast triggered 10m ago

Showing 1 of 1 · demo-wired ≠ production-live

Why this matters

Risk Guardrail bots does NOT propose intents or sign orders; only permits or blocks. Understanding the authority boundary prevents misuse and makes promotion-gate reviews faster and more reliable. View raw spec JSON →
Polytraders Operator UX Mock · INTERNAL · demo-wired ≠ production-live · the plan · reason codes · shadow-mode pipeline
⚙ Page Configuration
Current page settings
Loading configuration…