Framework

Behavioral Intelligence Framework

How to characterize, monitor, and respond to behavioral patterns in decision systems.

v0.1·working·Updated July 2026

Overview

A decision is not fully characterized by its average outcome. Two strategies with identical returns can exhibit fundamentally different behavioral signatures — one steady and predictable, the other volatile and regime-dependent. Average performance masks the behavioral structure that determines how a decision will perform in conditions it has not yet encountered.

The Behavioral Intelligence Framework provides the architecture for observing, classifying, and responding to behavioral patterns in decision systems. It moves beyond aggregate metrics to characterize how decisions behave under stress, across regime transitions, over time, and relative to each other. Behavioral intelligence is what transforms a collection of qualified decisions into a portfolio whose risks are understood, not just measured.

This framework is diagnostic, not prescriptive. It does not decide what to do about behavioral patterns — that belongs to allocation and risk management. It decides what to see. The value of behavioral intelligence is in surfacing distinctions that aggregate metrics hide, so that downstream systems can make better-informed decisions about resource deployment.

Design Principles

These are governing constraints, not guidelines. Every architectural decision in the framework must be traceable to one of these principles.

01

Behavior Reveals Structure

The behavioral signature of a decision reveals more about its underlying structure than its parameter configuration.

Two strategies with identical parameters can behave differently because of subtle interactions between entry timing, exit mechanics, and environmental sensitivity. Observing behavior directly — rather than inferring it from parameters — captures these emergent properties.

02

Patterns Precede Outcomes

Behavioral degradation is observable before it produces measurable outcome degradation.

A strategy does not go from profitable to unprofitable in a single trade. The behavioral signature shifts first — win rate erosion, drawdown pattern changes, increasing fee sensitivity. Detecting these patterns early enables response before capital is lost.

03

Regime Context Is Essential

Behavioral patterns are only meaningful in the context of the environmental regime in which they occur.

A drawdown during a trending regime has different implications than the same drawdown during a choppy regime. Without regime context, behavioral classification conflates environmental effects with strategy-level degradation.

04

Behavior Is Evidence

Observed behavioral patterns constitute evidence that should inform qualification, allocation, and learning systems.

Behavioral intelligence is not decorative analytics. It produces structured evidence that other systems consume — qualification uses it for re-assessment, allocation uses it for ranking, and learning uses it for generation guidance.

System Map

Five layers from raw observation to system response. Observations are collected continuously. Patterns are extracted on batch cadence. Classification maps patterns to behavioral states. Monitoring tracks state changes. Response propagates behavioral intelligence to downstream consumers.

1
Observation3 components
Trade Outcome CollectorEquity Curve TrackerRegime Context Annotator
2
Pattern Extraction3 components
Win Rate AnalyzerDrawdown Pattern DetectorFee Sensitivity Analyzer
3
Classification3 components
Behavioral State ClassifierRegime Sensitivity ProfilerCorrelation Profiler
4
Monitoring2 components
Degradation MonitorAnomaly Detector
5
Response2 components
Alert RouterIntelligence Publisher
Intelligence flows down|Evidence flows up

Layers & Components

Each layer has distinct responsibilities, inputs, outputs, and ownership. No component spans multiple layers.

1

Observation

Collects raw behavioral data from execution, simulation, and market context. The foundation layer that all pattern extraction depends on.

Trade Outcome Collector

Records individual trade outcomes with full context — entry conditions, exit mechanics, regime, timing

In: Closed positions, Entry signals, Exit audit trailOut: Enriched trade records with MAE/MFE, drift, mechanism attributionOwns: Position exit audit trail, decision fingerprints

Equity Curve Tracker

Maintains continuous equity curves for behavioral time-series analysis

In: Paper/live account snapshots, Mark-to-market valuesOut: Per-strategy equity curves, Portfolio-level equity curvesOwns: Account snapshot history, equity curve storage

Regime Context Annotator

Tags every observation with the environmental regime in which it occurred

In: Market context snapshots, Regime classifier outputOut: Regime-annotated observationsOwns: Regime label assignment, context snapshot linkage
2

Pattern Extraction

Transforms raw observations into structured behavioral patterns using statistical and ML-based methods.

Win Rate Analyzer

Tracks win rate evolution over rolling windows, detecting erosion and recovery

In: Trade outcome history, Regime contextOut: Rolling win rate series, Win rate trend classificationOwns: Rolling window computation, trend detection thresholds

Drawdown Pattern Detector

Classifies drawdown behavior — frequency, depth, recovery time, regime sensitivity

In: Equity curves, Regime transitionsOut: Drawdown profiles, Recovery reliability scoresOwns: Drawdown classification, recovery pattern analysis

Fee Sensitivity Analyzer

Detects strategies whose returns are eroded by transaction costs

In: Trade outcomes, Average trade return, Trade frequencyOut: Fee-bleeder classification, Fee efficiency ratioOwns: Rolling 20-trade window analysis, 0.3% round-trip fee threshold
3

Classification

Maps extracted patterns into behavioral categories that downstream systems can act on.

Behavioral State Classifier

Assigns each strategy a current behavioral state based on composite pattern analysis

In: Pattern extraction outputs, Regime context, Historical baselinesOut: Behavioral state label (healthy/degrading/anomalous/recovering)Owns: State classification logic, threshold calibration

Regime Sensitivity Profiler

Characterizes how each strategy responds to different environmental regimes

In: Per-regime performance data, Transition historyOut: Regime sensitivity profile, Transition survivability scoresOwns: Per-strategy regime transition matrix, survivability computation

Correlation Profiler

Maps behavioral similarity across strategies to detect hidden concentration

In: Equity curve pairs, Strategy parametersOut: Correlation matrix, Portfolio diversity score, High-correlation pair warningsOwns: Pearson correlation computation, diversity scoring
4

Monitoring

Tracks behavioral state changes over time. Detects transitions between states and generates alerts.

Degradation Monitor

Detects sustained behavioral degradation — not single bad trades, but patterns of decline

In: Behavioral state history, Pattern trend dataOut: Degradation alerts, Severity classificationsOwns: Degradation detection logic, alert emission, consecutive miss counting

Anomaly Detector

Identifies behavioral patterns that deviate significantly from established baselines

In: Current behavioral metrics, Historical baselines, Regime contextOut: Anomaly flags (level shift, trend break, volatility spike)Owns: SPC-based anomaly detection (M6 model), shadow mode scoring
5

Response

Propagates behavioral intelligence to downstream consumers. Advisory — does not autonomously take action.

Alert Router

Directs behavioral alerts to appropriate consumers — qualification, allocation, learning

In: Degradation alerts, Anomaly flags, State transitionsOut: Structured alert records in alert_log, Evaluation dimension entriesOwns: Alert routing logic, consumer mapping

Intelligence Publisher

Makes behavioral intelligence available to downstream decision systems

In: Behavioral classifications, Regime sensitivity profiles, Correlation dataOut: strategy_evaluations entries, Allocation intelligence inputs, Learning summary contributionsOwns: Evidence formatting for downstream consumers, staleness tracking

States & Transitions

A decision moves through these states as it accumulates evidence. Each transition is gated — there are no free promotions.

Healthy
Degrading
Anomalous
Recovering

Healthy

Behavioral patterns are within expected ranges. No degradation signals. Performance consistent with qualification evidence.

Entry: All behavioral dimensions within baseline thresholds for current regime

Exits: Sustained pattern deviation -> Degrading · Sudden anomaly -> Anomalous

Degrading

Behavioral patterns show sustained negative trends. Not yet anomalous, but trajectory is concerning. Advisory alerts emitted.

Entry: Rolling metrics show sustained decline (win rate erosion, increasing drawdown frequency, fee-bleeder detection)

Exits: Patterns stabilize -> Healthy · Degradation accelerates -> Anomalous · Regime change explains pattern -> Healthy (with regime annotation)

Anomalous

Behavioral patterns deviate significantly from all historical baselines. Requires investigation. Strong advisory signals emitted.

Entry: Statistical anomaly detected — level shift, trend break, or volatility spike beyond SPC thresholds

Exits: New baseline established -> Degrading (re-baselined) · Anomaly resolves -> Recovering

Recovering

Previously degraded or anomalous, now showing positive behavioral trend. Confidence rebuilding.

Entry: Positive trend reversal after degrading or anomalous state, sustained for minimum observation window

Exits: Full recovery to baseline -> Healthy · Recovery stalls -> Degrading

FromToTriggerGuard
HealthyDegrading6h evaluation batch detects sustained negative trendMultiple pattern dimensions showing decline over 5+ data points
HealthyAnomalousAnomaly detector firesSPC threshold breach on level shift, trend break, or volatility
DegradingAnomalousDegradation accelerates beyond anomaly thresholdsPattern deviation exceeds 3-sigma from historical baseline
DegradingHealthyPatterns return to baseline rangesSustained recovery over minimum observation window
AnomalousRecoveringAnomaly resolves, positive trend emergesMetrics moving toward historical baseline for 3+ evaluation periods
RecoveringHealthyFull return to baseline behavioral rangesAll pattern dimensions within expected ranges for current regime
RecoveringDegradingRecovery stalls or reversesPositive trend ceases, metrics plateau or resume decline

Boundary Rules

Boundaries define what crosses between layers and what does not. Every boundary has an explicit failure mode.

Observation -> Pattern Extraction

Crosses

Individual trade records with full context, equity curve data points, regime-annotated timestamps

Does Not Cross

Raw market data, tick-level execution details, order book state

Failure Mode

Missing observations -> pattern extraction operates on incomplete data, confidence flags lowered.

Pattern Extraction -> Classification

Crosses

Structured pattern metrics — rolling statistics, trend classifications, fee ratios

Does Not Cross

Individual trade details, raw equity curves, computation methodology

Failure Mode

Insufficient pattern data -> classification returns 'insufficient_data' rather than a false healthy signal.

Classification -> Monitoring

Crosses

Behavioral state labels with confidence, regime context, comparison to baselines

Does Not Cross

Classification model internals, threshold tuning parameters, alternative classifications considered

Failure Mode

Classification failure -> monitoring retains previous state (conservative). No silent state changes.

Monitoring -> Response (External Systems)

Crosses

Advisory alerts, behavioral intelligence summaries, structured evaluation entries

Does Not Cross

Binding directives. Behavioral intelligence advises — it never autonomously pauses, kills, or reallocates.

Failure Mode

Alert delivery failure -> logged but non-fatal. Behavioral intelligence is advisory; its absence degrades quality but does not break execution.

Operational Semantics

How this framework operates in practice — cadence, consumers, and staleness rules.

DimensionValueRationale
Observation collectionContinuous (every closed position, every snapshot)Observations are the raw material. Missing observations cannot be reconstructed. Collection is continuous and append-only.
Pattern extraction cadenceEvery 6 hours (evaluation batch)Pattern extraction is computationally meaningful only with sufficient new data. 6h batch aligns with qualification assessment cadence.
Classification updateEvery 6 hours (evaluation batch)Behavioral state is updated alongside pattern extraction. Consumers read the latest classification on their own cadence.
Anomaly detectionEvery 6 hours (M6 model, shadow mode)SPC-based anomaly detection runs in eval batch. Currently shadow mode — scores stored in evaluation inputs, not yet triggering actions.
Correlation computationEvery 6 hours (M5 model)Portfolio correlation matrix recomputed each eval batch. Feeds diversity scoring and allocation intelligence.
Alert retentionIndefinite (alert_log table)Behavioral alerts are historical evidence. They inform learning systems and audit trails. Never deleted.
Rolling window size20 trades (fee-bleeder), regime-duration-aware (other patterns)Window sizes balance recency against statistical reliability. Fee-bleeder uses fixed 20-trade window; other patterns adapt to regime duration.

Knowledge Lineage

Related Research

See this framework implemented in Orqis

Research — Warren Labs | Orqis