Skip to content
Public LQM Registry

Inspect the models, not just the marketing.

Every public built-in LargeQuant model exposes its family, version, runtime, input contract, output contract and default parameters. Finance-specific private/internal model brands are intentionally excluded from this public registry.

33public built-in model versions
20model families
1.0public registry contract
BACKTESTING1.0.0

Signal Strategy Backtester

lq.backtest.signal-strategy

Lagged-signal strategy backtest with look-ahead guard, transaction costs, turnover, drawdown and risk-adjusted performance metrics.

cpubacktestinglookahead-guard
python-processInspect model →
DATA-INTELLIGENCE1.0.0

Streaming Time-Series Quality Profile

lq.data.time-series-profile

Profiles ordered numerical streams for timestamp monotonicity, duplicates, cadence gaps and robust MAD outliers before downstream quantitative research.

cpudata-intelligencestreamingqualitytime-series
python-processInspect model →
DECISION1.0.0

Evidence-Backed Adaptive Model Router

lq.decision.adaptive-router

Selects a champion or adaptive ensemble from candidate performance histories using recency weighting, optional regime conditioning, minimum-evidence guards and switching margins.

cpudecisionadaptiveregime-awarechampion-challenger
python-processInspect model →
DETERMINISTIC1.0.0

Weighted Sum

lq.math.weighted-sum

Deterministic weighted aggregation with explicit weights and reproducible arithmetic.

cpudeterministicgoverned
php-nativeInspect model →
ECONOMETRICS1.0.0

VAR(1) Multivariate Econometric Model

lq.econometrics.var1

Multivariate VAR(1) estimation by OLS with residual covariance, per-series diagnostics and recursive multi-step forecasts.

cpueconometricsmultivariateforecasting
python-processInspect model →
ENSEMBLE1.0.0

Adaptive Exponential-Weights Ensemble

lq.ensemble.exponential-weights

Recency-aware exponential weighting over candidate loss histories with deterministic champion selection and effective-model-count diagnostics.

cpuensembleadaptivemodel-selection
python-processInspect model →
EVALUATION1.0.0

Prequential Forecast Evaluation

lq.evaluation.prequential-forecast

Online one-step-ahead evaluation of naive, AR(1) and linear-trend forecasters using only information available before each realized observation.

cpuevaluationstreamingforecastingprequential
python-processInspect model →
FORECASTING1.0.0

AR(1) Residual-Bootstrap Forecast

lq.forecasting.ar1-residual-bootstrap

Seeded empirical residual bootstrap around an AR(1) process, producing distributional forecasts, quantile intervals and reproducible sample paths.

cpuforecastingprobabilisticbootstrapseeded
python-processInspect model →
FORECASTING1.0.0

Linear Trend Forecast

lq.forecasting.linear-trend

OLS time-trend forecast with residual uncertainty intervals. Quantitative output only; no language generation.

cpu
python-processInspect model →
MEMORY1.0.0

Quantitative Memory Performance Profile

lq.memory.performance-profile

Summarizes signed quantitative-memory observations by candidate, recency and current regime to produce reproducible performance profiles.

cpumemoryperformanceregime-aware
python-processInspect model →
MONITORING1.0.0

Page-Hinkley Sequential Drift Detector

lq.monitoring.page-hinkley

Sequential Page-Hinkley drift detector for realized errors, residuals or other numerical monitoring streams with explicit alarm indices and drift statistics.

cpumonitoringdriftsequential
python-processInspect model →
MONITORING1.0.0

Two-Sided CUSUM Drift Detector

lq.monitoring.two-sided-cusum

Sequential two-sided cumulative-sum detector for upward or downward shifts in realized error, residual, risk or other quantitative streams.

cpumonitoringdriftstreamingsequential
python-processInspect model →
OPTIMIZATION1.0.0

Capacity allocation

lq.optimization.capacity-allocation

Exact bounded integer capacity allocation, with a first-fit baseline and scoped assessment of a supplied allocation.

cpudeterministicgoverned
php-nativeInspect model →
OPTIMIZATION1.0.0

Constrained Mean-Variance Optimizer

lq.optimization.mean-variance

Long-only capped portfolio optimisation using projected-gradient optimisation on expected returns and covariance.

cpu
python-processInspect model →
REGIME1.0.0

Structural Break Detector

lq.regime.structural-break

Exhaustive two-regime least-squares mean-shift scan with fit-improvement and standardized-shift diagnostics.

cputime-seriesregime
python-processInspect model →
REGIME1.0.0

Two-State Gaussian HMM Regime Model

lq.regime.gaussian-hmm2

Deterministic two-state Gaussian hidden Markov model estimated with scaled Baum-Welch EM, emitting state probabilities, transition persistence, regime separation and current latent-state classification.

cpuregimehidden-stateprobabilistictime-series
python-processInspect model →
RESEARCH1.0.0

Autonomous Challenger Research Cycle

lq.research.challenger-cycle

Prequential champion/challenger evaluation with sequential error-drift monitoring and explicit evidence-based recommendation to hold, challenge or initiate fresh research.

cpuresearchautonomousstreamingdrift
python-processInspect model →
RESEARCH1.0.0

Rolling Probabilistic Forecast Calibration

lq.research.rolling-forecast-calibration

Out-of-sample rolling AR(1) residual-bootstrap calibration with empirical interval coverage, width, interval score and explicit look-ahead guard.

cpuresearchprobabilisticcalibrationwalk-forward
python-processInspect model →
RESEARCH1.0.0

Walk-Forward AR(1) Research Study

lq.research.walk-forward-ar1

Out-of-sample one-step AR(1) evaluation against a naive last-value baseline with explicit look-ahead guard and LQBench skill metrics.

cpuresearchwalk-forwardlqbench
python-processInspect model →
RESEARCH1.0.0

Walk-Forward Forecast Model Competition

lq.research.forecast-model-competition

Out-of-sample competition among naive, AR(1) and linear-trend forecasters with deterministic winner selection or inverse-RMSE ensemble weighting.

cpuresearchforecastingensemblemodel-selection
python-processInspect model →
RISK1.0.0

Dynamic EWMA Covariance & Correlation

lq.risk.dynamic-ewma-covariance

Multivariate exponentially weighted covariance engine with current covariance, correlation, volatility and a bounded covariance-path tail for dynamic risk monitoring.

cpuriskcovariancecorrelationmultivariate
python-processInspect model →
RISK1.0.0

Historical VaR & Expected Shortfall

lq.risk.historical-var

Empirical historical Value at Risk, CVaR/Expected Shortfall, volatility and drawdown from a return series.

cpu
python-processInspect model →
RISK1.0.0

Probabilistic Portfolio Risk Surface

lq.risk.probabilistic-surface

Seeded multivariate Monte Carlo risk surface across multiple horizons and confidence levels, emitting Value at Risk, Expected Shortfall and P&L distribution summaries.

cpuriskprobabilisticmonte-carlomultivariate
python-processInspect model →
SCENARIO1.0.0

Portfolio Stress Scenario Engine

lq.scenario.portfolio-stress

Deterministic delta-gamma portfolio stress revaluation across named shock scenarios with worst/best and tail-loss summaries.

cpuscenariostress-testing
python-processInspect model →
SIMULATION1.0.0

Correlated Multi-Asset GBM Simulator

lq.simulation.correlated-gbm

Seeded multi-asset geometric Brownian motion using a validated covariance matrix and Cholesky-correlated innovations.

cpusimulationmultivariate
python-processInspect model →
SIMULATION1.0.0

Geometric Brownian Motion Simulator

lq.simulation.geometric-brownian-motion

Seeded stochastic path simulation with reproducible terminal distributions and sample paths.

cpu
python-processInspect model →
STATE-SPACE1.0.0

Local-Level State-Space Model

lq.state-space.local-level

Local-level Kalman filter with transparent process/observation variance assumptions, innovations and probabilistic state forecasts.

cpustate-spacekalman-filterprobabilistic
python-processInspect model →
STATISTICAL1.0.0

Descriptive Statistics

lq.statistics.descriptive

Auditable descriptive statistics for a numeric series, including dispersion and interpolated percentiles.

cpudeterministicgoverned
php-nativeInspect model →
STATISTICAL1.0.0

Linear Regression

lq.statistics.linear-regression

Ordinary least squares regression for one explanatory series with explicit fit diagnostics.

cpudeterministicgoverned
php-nativeInspect model →
STATISTICAL1.0.0

Pearson Correlation

lq.statistics.pearson-correlation

Deterministic Pearson product-moment correlation for two aligned numeric series.

cpudeterministicgoverned
php-nativeInspect model →
TIME-SERIES1.0.0

AR(1) Time-Series Forecast

lq.timeseries.ar1

Autoregressive AR(1) estimation and recursive forecasting with residual uncertainty propagation and stationarity diagnostics.

cputime-series
python-processInspect model →
VOLATILITY1.0.0

EWMA Volatility Model

lq.volatility.ewma

Exponentially weighted volatility estimator with explicit decay, annualization and volatility-path diagnostics.

cputime-seriesrisk
python-processInspect model →
VOLATILITY1.0.0

Variance-Targeted GARCH(1,1)

lq.volatility.garch11

GARCH(1,1) conditional volatility model using variance targeting and deterministic Gaussian quasi-likelihood search with persistence diagnostics.

cpuvolatilityeconometricsrisk
python-processInspect model →