Tail risk, regime transitions, and market-structure shifts — measured rigorously, validated forward, and claimed only when proven.
Quantifies the real-time probability of a market regime transition into crisis. The signal is pre-registered in our research log and evaluated forward-prospectively — not tuned on replayed historical crashes.
Separates genuine price momentum from microstructure noise and liquidity artifacts. Delivers a real-time signal quality score that tells you whether a move is driven by informed flow or temporary friction.
Monitors the structural stability of asset relationships in real time. Instead of trading on a fixed schedule, our architecture identifies exactly when portfolio factor exposures have shifted enough to warrant action — delivering measurably higher risk-adjusted returns per rebalance event.
Classifies the current market environment into one of four distinct regimes on a continuous coordinate system. Each regime maps to a measurably optimal allocation strategy, replacing subjective regime labels with quantitative precision.
Combines topological analysis of market microstructure with regime transition modeling. Detects when the geometry of return distributions is shifting before it becomes visible in price or volatility.
Analyzes how market dynamics shift across timescales — from intraday through weekly. Cross-scale divergence surfaces when short- and long-horizon dynamics decouple and feeds the regime read as one input among several — treated as a hypothesis under forward validation, not a settled early-warning signal.
Primary crash signal spanning SPY, QQQ, IWM, DIA, and EEM, with a frozen threshold and lead-time window pre-registered in our research log. It continues live tracking for prospective Harvey-significance validation — a forward, out-of-sample evaluation rather than a retrospective replay of historical stress events.
A multi-asset research book runs live and continuously — equities, digital assets, and derivatives — as the prospective, out-of-sample test bed for the signal registry. Allocation and risk management operate automatically so that every frozen-threshold hypothesis accrues genuine forward observations, not in-sample fits.
Every signal has a pre-registered hypothesis with defined null conditions, required sample sizes, and multiple-testing correction. Over 65,000 prospective observations recorded across the registry. Validation architecture enforces statistical discipline automatically — signals are not promoted to live sizing until they clear the Harvey 2016 t>3 threshold on a frozen sample.
Our research model submits weekly to the Numerai Signals blind tournament for independent third-party validation. Resolved rounds counted here; full per-round scores published on the performance page. We do not claim a score until the tournament’s own robust-evaluation quorum is reached — Numerai’s Alpha metric requires a multi-month track record before it stabilises.
The foundational whitepaper. Develops a drift-diffusion architecture for decomposing asset dynamics, regime transition modeling via potential barrier analysis, and multi-scale signal construction with connections to 85+ works in the literature.
A self-contained pedagogical treatment bridging mathematical physics and quantitative finance. Designed for practitioners who want to understand the analytical foundations without a physics background.
Survey of 142 papers across 18 thematic areas spanning portfolio optimization, factor investing, regime detection, and cross-disciplinary quantitative methods. Maps the full research landscape informing our signal development.
Describes the architecture of our autonomous portfolio management engine. Signal integration, adaptive position sizing, risk controls, execution logic, and the feedback loop between signals and allocation decisions.
Recent work on topological data analysis applied to market regime classification. Persistence landscapes provide stable, vectorizable features from return point clouds — directly relevant to our structural breakdown detection capabilities.
Extends classical stochastic volatility with barrier-crossing corrections for tail events. Our tail risk probability architecture builds on this class of methods, adding multi-scale calibration and empirical validation against five major indices.
Our factor-stability signals flagged elevated instability in equity correlations through the April 2025 tariff volatility. Risk-responsive rebalancing reduced exposure into the turbulence relative to a static allocation.
Hypothesis registered in our research log with a pre-frozen threshold and lead-time window. Validation is forward-prospective under the Harvey quorum (N ≥ 20 live observations) — not via retrospective replay of historical stress events.
Survey of stochastic drift-decomposition methods applied to signal extraction in quantitative finance. Provides theoretical grounding for separating genuine momentum from market microstructure noise in real time.
Download a sample report, or reach out to discuss how Quark fits your workflow.