Built on observation

The architecture beneath every regime call

The framework does not predict prices. It classifies the conditions that make prices possible — then watches for the hairline fractures that precede regime change. Every threshold, every weight, every data source is documented here for scrutiny.
Hero Image
Four-stage pipeline
Documented thresholds
Cycle-tested logic
Published limitations

Liquidity is not a single variable but a shifting landscape. The framework identifies four distinct regimes, each with characteristic behaviors, vulnerabilities, and transition triggers. Understanding these states transforms how practitioners interpret market events.

In the abundant regime, capital flows freely and spreads remain tight. Market makers compete aggressively, execution costs stay low, and large orders absorb with minimal price impact. This is the environment most participants assume is permanent — and it is precisely this assumption that makes the transition to tighter conditions so painful.
The normal regime represents a sustainable middle ground where liquidity is sufficient but not effortless. Spreads widen modestly during stress, depth fluctuates with sentiment, and execution requires more care than in abundant conditions. Most historical market periods have unfolded within this state.

Tight regimes emerge when capital becomes selective. Market makers withdraw, spreads gape, and depth evaporates at critical price levels. What appears as volatility is often structural scarcity — the market's plumbing constricting while participants continue trading as if nothing has changed.

Crisis regimes represent a breakdown of normal market function. Liquidity does not merely tighten; it fragments. Correlations spike, safe assets become unsafe, and the mechanisms that ordinarily stabilize prices become amplifiers of distress. These periods are brief but transformative, rewriting assumptions that held for years.

From raw data to regime clarity

A four-stage analytical pipeline that transforms market noise into structural awareness practitioners can act upon with confidence.

01

Multi-source data ingestion

Order book feeds from primary exchanges, execution data from institutional venues, and macro-financial indicators are ingested, cross-referenced, and validated. Discrepancies are flagged rather than smoothed, preserving the irregularities that often precede structural shifts.

02

Regime classification engine

Spread decomposition, depth profiling, and execution pattern analysis classify current conditions into one of four liquidity regimes. Thresholds are derived from empirical observation across multiple market cycles, not fitted to recent history alone.

03

Transition probability modeling

Macro overlays assess whether microstructure signals reflect local distortions or systemic shifts. Funding conditions, central bank operations, and cross-asset correlations are weighed to estimate the probability and likely direction of regime change.

04

Forecast generation with intervals

Regime assessments are issued with explicit confidence intervals, known limitations, and historical analogues. Practitioners receive updates as conditions evolve, enabling adaptive positioning rather than reactive trading.

Where conventional models falter

Traditional volatility-based risk frameworks miss the structural dimension entirely. The comparison below illustrates where conventional approaches fail during regime transitions.

Feature
Miurqotyathe
Standard models
Volatility as risk proxy
Regime-conditional thresholds
Order book depth analysis
Published methodology limits
Macro-microstructure integration
Historical cycle testing

Framework performance across market cycles

The methodology has been refined through observation of multiple liquidity environments, from calm periods to structural stress events.

Metrics reflect a focused team with deep expertise and growing institutional recognition, not inflated claims or unverifiable figures.
Steady growth
7+

Years in development

The framework evolved from an academic working paper through iterative refinement, institutional feedback, and live market observation across diverse conditions.
Expanding reach
40+

Institutional users

A growing base of family offices, hedge funds, and research desks relies on regime briefings for structural market awareness and risk context.

Selective hiring
12

Core team members

An experienced group of quantitative researchers, macro strategists, data engineers, and policy analysts dedicated to transparent, rigorous analysis.
Proven resilience
3

Major cycle tests

The framework has been stress-tested through distinct market environments, with classification accuracy and transition signals evaluated against live outcomes.

Explore the framework further

1

Review case studies

Examine how the framework classified specific historical periods, from the gradual tightening of 2018 to the abrupt fragmentation of March 2020. Each case includes the data observed, the classification logic applied, and the limitations acknowledged at the time.

2

Read methodology notes

Access detailed documentation on threshold derivation, data sources, model limitations, and revision history. The team publishes these materials so practitioners may evaluate the logic independently.

3

Compare regime archives

Browse the complete historical record of regime classifications, transition probabilities, and forecast intervals. Observe how the framework performed across multiple market cycles and structural shifts.

4

Contact the research team

Submit technical questions, request clarification on classification decisions, or discuss how the framework might complement your existing analytical process. Responses arrive within one business day.