Expand description
Advanced market microstructure analytics for Orderflow.
§of_analytics
of_analytics contains additive advanced market microstructure analytics for
Orderflow. The crate exists so heavier analytics can evolve outside of_core
without breaking existing AnalyticsAccumulator, runtime, C ABI, Python, or
Java APIs.
of_analytics starts at 0.1.0 in the broader Orderflow 0.5.0 development
line because it is a new public Rust surface.
The first foundation is dependency-light:
- market-quality/TCA primitives for quoted spread, effective spread, realized spread, price improvement, quote freshness, and side-aware slippage,
- execution-quality/TCA primitives for implementation shortfall, arrival and decision slippage, adverse selection, trade-through, and fill-quality score,
- liquidity/depth primitives for top-of-book depth, multi-level depth, proportional imbalance, order-flow imbalance, depth slope, depth convexity, book pressure, replenishment/depletion rates, drought detection, and sweepability,
- market-impact primitives for Kyle-style lambda, Amihud-style illiquidity, calibrated expected impact, square-root impact, temporary/permanent impact, impact decay, and child-order attribution,
- VPIN-style fixed-bucket toxicity primitives plus post-trade markout, adverse-selection, quote-fade, toxic-burst, and informed-flow proxy signals,
- fixed-window volatility/noise primitives with bipower variation, jump variation, OHLC range estimators, signature-plot points, and intraday seasonality buckets,
- threshold-based market regime classification plus composite trend/range/chop, liquidity, spread, session, hidden-liquidity, and transition-confidence labels,
- feed-quality primitives for sequence gaps, out-of-order events, duplicates, stale events, locked/crossed books, timestamp skew, resets, health scoring, replay usability, primary issue selection, and operator review reports,
- feature-vector primitives for stable feature ids, ordered schemas, schema hashes, missing-value policy, quality labels, and reusable fixed-capacity writers,
- resiliency primitives for threshold-based spread/depth shock detection, recovery timing, and liquidity resiliency scoring,
- queue/fill primitives for passive queue position estimates, fill probability, expected time-to-fill, amend queue loss, top-level survival, cancel/replace cost, and maker/taker decision scoring,
- pattern-risk primitives for spoofing/layering, quote-stuffing, stop-run, absorption, momentum-ignition, iceberg, hidden accumulation/distribution, stacked-imbalance, and failed-breakout risk indicators,
- venue/route primitives for fill, reject, cancel, latency, route-health, venue-liquidity, toxicity, fill-quality, reliability, route-quality, drift, and degradation diagnostics,
- cross-asset primitives for rolling correlation, beta, pair divergence, thresholded basis pressure, latency-adjusted correlation, cross-venue divergence, ETF/component imbalance, and relationship-degradation diagnostics,
- derivatives primitives for put/call pressure, volume/open-interest anomaly, implied-volatility flow, gamma exposure, IV skew, term structure, implied-versus-realized richness, gamma pressure, futures basis, roll pressure, funding divergence, and aggregate derivatives stress,
- explicit feature profiles so users can opt into future impact, toxicity, volatility, regime, data-quality, feature-vector, resiliency, queue-fill, cross-asset, pattern, derivatives, institutional, and ML feature modules without forcing all downstream users to compile them.
The crate does not submit orders, manage runtime state, own persistence, or
replace existing of_core APIs. It consumes normalized market data and returns
typed snapshots that hosts can wire into runtime, research, or execution
systems.
§Feature Profiles
Default features:
market-qualityliquidity
Reserved additive profiles:
impacttoxicityvolatilityregimedata-qualityfeature-vectorresiliencyqueue-fillcross-assetpatternsderivativesinstitutionalml-featuresall
§Public API Meaning
The analytics types are typed calculators and snapshots, not hidden strategy decisions. Context types such as quote, trade, depth, route, derivative, and feature inputs carry normalized observations and timestamps. Tracker or calculator types accumulate a bounded window; snapshot types expose the result without mutating the input observation. Constructors validate units, capacities, thresholds, and required metadata before a tracker is used.
The market-quality and execution-quality surfaces explain spread, slippage, impact, adverse selection, and fill outcomes. Liquidity, queue, resiliency, toxicity, pattern-risk, volatility, regime, cross-asset, and derivatives surfaces answer distinct analytical questions rather than producing one universal signal. Feature vectors and model metadata define stable input ordering and quality/missing-value semantics for downstream models.
All profiles are additive feature boundaries. A feature flag controls compile
cost and dependency inclusion; it does not silently change the meaning of
existing of_core snapshots. These calculations do not place orders, own
persistence, or override DataQualityFlags; hosts remain responsible for
quality gating, replay validation, and execution risk.
§Market Quality Example
use of_analytics::{MarketQualityTracker, QuoteContext, TradeContext};
use of_core::Side;
let mut tracker = MarketQualityTracker::new(1_000_000);
tracker.on_quote(QuoteContext::new(499_975, 500_025, 100, 120, 1_000)?);
let snapshot = tracker.evaluate_trade(
TradeContext::new(500_050, 10, Side::Ask, 1_500)?,
Some(500_075),
)?;
assert_eq!(snapshot.quoted_spread(), 50);
assert!(snapshot.effective_spread_bps() > 0);§Execution Quality Example
use of_analytics::{ExecutionBenchmark, ExecutionQualityAnalyzer, TradeContext};
use of_core::Side;
let trade = TradeContext::new(101_000, 10, Side::Ask, 1)?;
let benchmark = ExecutionBenchmark::new(
100_000,
100_500,
99_950,
100_050,
Some(100_750),
)?;
let snapshot = ExecutionQualityAnalyzer::evaluate(trade, benchmark);
assert!(snapshot.implementation_shortfall_bps() > 0);
assert!(snapshot.trade_through());§Liquidity Example
use of_analytics::{
LiquidityDepthAnalyzer, LiquidityFlowConfig, LiquidityFlowEvent,
LiquidityFlowTracker,
};
use of_core::BookLevel;
use of_core::Side;
let bids = [
BookLevel { level: 0, price: 499_975, size: 100 },
BookLevel { level: 1, price: 499_950, size: 80 },
BookLevel { level: 2, price: 499_925, size: 70 },
];
let asks = [
BookLevel { level: 0, price: 500_025, size: 120 },
BookLevel { level: 1, price: 500_050, size: 90 },
BookLevel { level: 2, price: 500_075, size: 60 },
];
let snapshot = LiquidityDepthAnalyzer::new(3).analyze(&bids, &asks, 150)?;
assert_eq!(snapshot.bid_depth(), 250);
assert_eq!(snapshot.ask_depth(), 270);
assert!(snapshot.sweepable_buy_qty() >= 120);
assert!(snapshot.book_pressure_bps() < 0);
let mut flow = LiquidityFlowTracker::new(LiquidityFlowConfig::default());
flow.on_event(LiquidityFlowEvent::new(Side::Bid, 100, 0, 0, 1)?);
flow.on_event(LiquidityFlowEvent::new(Side::Ask, 0, 250, 25, 500_000_001)?);
assert!(flow.snapshot().order_flow_imbalance_bps() > 0);§Impact And Toxicity Example
use of_analytics::{
ExpectedImpactEstimator, ExpectedImpactInput, ImpactCalibration,
ImpactSample, ImpactTracker, ToxicityAnalyzer, ToxicityConfig,
ToxicityInput, TradeContext, VpinTracker,
};
use of_core::Side;
let mut impact = ImpactTracker::new();
impact.on_sample(ImpactSample::new(500_000, 501_000, 100, 50_000_000)?);
assert!(impact.snapshot().kyle_lambda_ppm() > 0);
let calibration = ImpactCalibration::new(
1_000_000,
200,
10_000,
500,
250,
1_000_000_000,
)?;
let estimate = ExpectedImpactEstimator::estimate(ExpectedImpactInput::new(
Side::Ask,
1_000,
10_000,
100_000,
1_000_000_000,
calibration,
)?);
assert!(estimate.expected_total_impact_bps() > 0);
let mut vpin = VpinTracker::<4>::new(100)?;
vpin.on_trade(TradeContext::new(500_000, 80, Side::Ask, 1)?);
vpin.on_trade(TradeContext::new(500_000, 20, Side::Bid, 2)?);
assert_eq!(vpin.snapshot().bucket_count(), 1);
let toxicity = ToxicityAnalyzer::new(ToxicityConfig::default()).evaluate(
ToxicityInput::new(
TradeContext::new(100_000, 10, Side::Ask, 1)?,
100_500,
1_000,
1_000,
1_000,
500,
8_000,
7_000,
)?,
);
assert!(toxicity.toxic_flow_burst());§Volatility And Regime Example
use of_analytics::{
CompositeRegimeClassifier, CompositeRegimeInput, OhlcVolatilityEstimator,
OhlcVolatilityInput, RegimeClassifier, RegimeInput, RegimeKind,
SessionRegimeKind, TrendRegimeKind, VolatilitySeasonalityTracker,
VolatilitySignatureEstimator, VolatilityTracker,
};
let mut vol = VolatilityTracker::<8>::new()?;
vol.on_price(100_000)?;
vol.on_price(101_000)?;
vol.on_price(100_500)?;
let snapshot = vol.snapshot();
assert!(snapshot.bipower_vol_bps() > 0);
let regime = RegimeClassifier::default().classify(RegimeInput::new(
5,
snapshot.realized_vol_bps(),
0,
0,
));
assert!(matches!(regime.kind(), RegimeKind::Normal | RegimeKind::Volatile));
let composite = CompositeRegimeClassifier::default().classify(
CompositeRegimeInput::new(
8_000,
1_000,
1,
20,
2_000,
3_600_000_000_000,
3_600_000_000_000,
false,
0,
0,
)?,
);
assert_eq!(composite.trend(), TrendRegimeKind::Trend);
assert_eq!(composite.session(), SessionRegimeKind::Continuous);
let ohlc = OhlcVolatilityEstimator::estimate(OhlcVolatilityInput::new(
100_000,
102_000,
99_000,
101_000,
Some(99_500),
)?);
assert!(ohlc.parkinson_vol_bps() > 0);
let signature = VolatilitySignatureEstimator::estimate(1_000_000, &[10, -10, 20, -20])?;
assert_eq!(signature.noise_ratio_bps(), 10_000);
let mut seasonality = VolatilitySeasonalityTracker::<2>::new(25)?;
seasonality.on_return(0, 10)?;
seasonality.on_return(0, -30)?;
assert_eq!(seasonality.snapshot(0)?.jump_count(), 1);§Data Quality Example
use of_analytics::{
FeedQualityConfig, FeedQualityEvent, FeedQualityFlags, FeedQualityTracker,
ReplayQualityAnalyzer,
};
let config = FeedQualityConfig::new(10, 20, 1)?;
let mut tracker = FeedQualityTracker::new(config);
tracker.on_event(FeedQualityEvent::new(
Some(10),
100,
105,
Some(99),
Some(101),
)?);
let flags = tracker.on_event(FeedQualityEvent::new(
Some(12),
110,
140,
Some(100),
Some(100),
)?);
assert!(flags.contains(FeedQualityFlags::SEQUENCE_GAP));
assert!(flags.contains(FeedQualityFlags::LOCKED_BOOK));
assert!(tracker.snapshot().health_score_bps() < 10_000);
let report = ReplayQualityAnalyzer::default().evaluate(tracker.snapshot());
assert!(report.operator_review_required());§Feature Vector Example
use of_analytics::{
FeatureDefinition, FeatureId, FeatureQuality, FeatureSchema, FeatureUnit,
FeatureVectorWriter, MissingValuePolicy,
};
let mut schema = FeatureSchema::<2>::new()?;
let spread = schema.register(FeatureDefinition::new(
FeatureId::new(1)?,
"spread_bps",
FeatureUnit::BasisPoints,
1,
MissingValuePolicy::Sentinel(-1),
)?)?;
schema.register(FeatureDefinition::new(
FeatureId::new(2)?,
"quality_bps",
FeatureUnit::ScoreBasisPoints,
1,
MissingValuePolicy::Zero,
)?)?;
let mut writer = FeatureVectorWriter::new(&schema);
writer.set(spread, 25, FeatureQuality::Good)?;
let vector = writer.finish();
assert_eq!(vector.values(), &[25, 0]);
assert_eq!(vector.schema_hash(), schema.schema_hash());§Resiliency Example
use of_analytics::{ResiliencyConfig, ResiliencySample, ResiliencyTracker};
let config = ResiliencyConfig::new(5, 1_000, 25, 5_000, 8, 9_000)?;
let mut tracker = ResiliencyTracker::new(config);
tracker.on_sample(ResiliencySample::new(100, 5, 500, 500)?);
let shock = tracker.on_sample(ResiliencySample::new(200, 30, 400, 400)?);
let recovered = tracker.on_sample(ResiliencySample::new(1_000_200, 7, 500, 500)?);
assert!(shock.active_shock());
assert_eq!(recovered.recovery_count(), 1);
assert_eq!(recovered.last_recovery_time_ns(), 1_000_000);§Queue And Fill Example
use of_analytics::{
QueueDecisionAnalyzer, QueueDecisionConfig, QueueDecisionInput,
QueueFillConfig, QueueFillTracker, QueueFillUpdate, QueuePositionEstimate,
QueueUpdateKind,
};
let config = QueueFillConfig::new(5_000, 100, 1_000_000_000)?;
let estimate = QueuePositionEstimate::new(100, 50, 200, 1)?;
let mut tracker = QueueFillTracker::new(config, estimate);
let snapshot = tracker.on_update(QueueFillUpdate::new(
QueueUpdateKind::Trade,
40,
160,
2,
)?);
assert_eq!(snapshot.qty_ahead(), 60);
assert!(snapshot.fill_probability_bps() > 0);
let decision = QueueDecisionAnalyzer::new(
QueueDecisionConfig::new(5_000, 5_000, 10_000_000_000)?,
)
.evaluate(QueueDecisionInput::new(
snapshot,
10,
5,
1,
2,
1,
1_000,
0,
0,
)?);
assert!(decision.maker_taker_decision_score_bps() > 0);§Pattern Risk Example
use of_analytics::{
PatternDetailAnalyzer, PatternDetailInput, PatternRiskClassifier,
PatternRiskInput, PatternRiskLiquidity,
};
let classifier = PatternRiskClassifier::default();
let snapshot = classifier.classify(PatternRiskInput::new(
800,
900,
10,
8_000,
5,
PatternRiskLiquidity::new(10, 1_000)?,
1_000_000,
)?);
assert!(snapshot.spoofing_layering_risk_bps() > 0);
assert!(snapshot.quote_stuffing_risk_bps() > 0);
let detail = PatternDetailAnalyzer::default().evaluate(
PatternDetailInput::new(8, 4, 1_000, 100, 4, 8_000, 500, 2, 30, 35, 1_000)?,
);
assert!(detail.iceberg_risk_bps() > 0);
assert!(detail.failed_breakout_risk_bps() > 0);§Venue Route Example
use of_analytics::{
VenueRouteEvent, VenueRouteEventKind, VenueRouteQualityAnalyzer,
VenueRouteQualityInput, VenueRouteTracker,
};
let mut tracker = VenueRouteTracker::new();
tracker.on_event(VenueRouteEvent::new(VenueRouteEventKind::Sent, 100, 0, 10)?);
tracker.on_event(VenueRouteEvent::new(VenueRouteEventKind::Fill, 60, 100, 20)?);
let snapshot = tracker.snapshot();
let quality = VenueRouteQualityAnalyzer::default().evaluate(
VenueRouteQualityInput::new(snapshot, 9_000, 500, 9_500, 9_500)?,
);
assert_eq!(snapshot.sent(), 1);
assert_eq!(snapshot.fills(), 1);
assert_eq!(snapshot.avg_quote_to_fill_latency_ns(), 100);
assert!(!quality.route_degraded());§Cross-Asset Example
use of_analytics::{
CrossAssetConfig, CrossAssetDiagnosticAnalyzer, CrossAssetDiagnosticInput,
CrossAssetSample, CrossAssetTracker,
};
let mut tracker = CrossAssetTracker::<8>::new(CrossAssetConfig::default())?;
tracker.on_sample(CrossAssetSample::new(100_000, 200_000, 1)?);
tracker.on_sample(CrossAssetSample::new(101_000, 202_000, 2)?);
tracker.on_sample(CrossAssetSample::new(102_000, 204_000, 3)?);
let snapshot = tracker.snapshot();
let diagnostic = CrossAssetDiagnosticAnalyzer::default().evaluate(
CrossAssetDiagnosticInput::new(snapshot, 1_000_000, 1_100_000, 5, 100)?,
);
assert!(snapshot.correlation_bps() > 0);
assert!(snapshot.lead_lag_score_bps() > 0);
assert!(diagnostic.synchronization_quality_bps() > 0);§Derivatives Example
use of_analytics::{
DerivativesDiagnosticAnalyzer, DerivativesDiagnosticInput,
DerivativesVolatilitySurface, FuturesBasisAnalyzer, FuturesBasisInput,
OptionFlowSample, OptionFlowTracker, OptionKind,
};
let mut options = OptionFlowTracker::new();
options.on_sample(OptionFlowSample::new(
OptionKind::Call,
100,
1_000,
50_000,
2_000,
1_000,
)?);
options.on_sample(OptionFlowSample::new(
OptionKind::Put,
200,
1_500,
150_000,
3_000,
-2_000,
)?);
assert!(options.snapshot().put_call_pressure_bps() > 0);
let basis = FuturesBasisAnalyzer::analyze(FuturesBasisInput::new(
100_000,
101_000,
100_500,
101_000,
102_000,
25,
)?);
let diagnostic = DerivativesDiagnosticAnalyzer::default().evaluate(
DerivativesDiagnosticInput::new(
options.snapshot(),
basis,
DerivativesVolatilitySurface::new(3_000, 3_500, 2_500, 3_000, 3_250, 2_000)?,
),
);
assert!(basis.basis_bps() > 0);
assert!(diagnostic.iv_richness_bps() > 0);§Low-Latency Principles
- No async runtime dependency.
- No heap allocation in hot update/evaluate methods.
- Borrow existing
of_corebook levels instead of copying snapshots. - Use integer arithmetic for prices, quantities, spreads, and basis points.
- Keep batch/research features separate from live hot-path trackers.
Structs§
- Child
Order Impact Analyzer - Deterministic child-order impact attribution analyzer.
- Child
Order Impact Context - Child-order impact attribution context.
- Child
Order Impact Snapshot - Child-order impact attribution snapshot.
- Composite
Regime Classifier - Deterministic composite regime classifier.
- Composite
Regime Config - Composite regime classifier configuration.
- Composite
Regime Input - Composite regime classifier input.
- Composite
Regime Snapshot - Composite regime snapshot.
- Cross
Asset Config - Cross-asset analytics configuration.
- Cross
Asset Diagnostic Analyzer - Deterministic cross-asset diagnostic analyzer.
- Cross
Asset Diagnostic Config - Cross-asset diagnostic thresholds.
- Cross
Asset Diagnostic Input - Cross-asset diagnostic input.
- Cross
Asset Diagnostic Snapshot - Cross-asset diagnostic snapshot.
- Cross
Asset Sample - Cross-asset paired price sample.
- Cross
Asset Snapshot - Cross-asset analytics snapshot.
- Cross
Asset Tracker - Fixed-window cross-asset lead/lag tracker.
- Derivatives
Diagnostic Analyzer - Deterministic derivatives diagnostic analyzer.
- Derivatives
Diagnostic Config - Derivatives diagnostic thresholds.
- Derivatives
Diagnostic Input - Derivatives diagnostic input.
- Derivatives
Diagnostic Snapshot - Derivatives diagnostic snapshot.
- Derivatives
Volatility Surface - Caller-supplied derivatives volatility surface summary.
- Execution
Benchmark - Execution-quality benchmark context.
- Execution
Quality Analyzer - Execution-quality/TCA analyzer.
- Execution
Quality Snapshot - Execution-quality/TCA snapshot.
- Expected
Impact Estimator - Deterministic pre-trade market-impact estimator.
- Expected
Impact Input - Pre-trade impact estimate input.
- Expected
Impact Snapshot - Pre-trade market-impact estimate.
- Feature
Definition - Feature definition inside a stable schema.
- Feature
Id - Stable feature identifier.
- Feature
Schema - Fixed-capacity feature schema.
- Feature
Vector - Completed fixed-capacity feature vector.
- Feature
Vector Writer - Reusable fixed-capacity feature-vector writer.
- Feed
Quality Config - Feed-quality tracker configuration.
- Feed
Quality Event - Market-data event context used by feed-quality analytics.
- Feed
Quality Flags - Feed-quality degradation flags.
- Feed
Quality Snapshot - Cumulative feed-quality snapshot.
- Feed
Quality Tracker - Allocation-free feed-quality tracker.
- Futures
Basis Analyzer - Futures basis analyzer.
- Futures
Basis Input - Futures basis input.
- Futures
Basis Snapshot - Futures basis snapshot.
- Impact
Calibration - Calibrated market-impact parameters for pre-trade estimates.
- Impact
Sample - Market-impact sample over a measurement interval.
- Impact
Snapshot - Cumulative market-impact snapshot.
- Impact
Tracker - Allocation-free cumulative impact tracker.
- Liquidity
Depth Analyzer - Borrowed depth analyzer.
- Liquidity
Depth Snapshot - Liquidity/depth snapshot over borrowed book levels.
- Liquidity
Flow Config - Liquidity-flow tracker configuration.
- Liquidity
Flow Event - Liquidity-flow event over a book observation interval.
- Liquidity
Flow Snapshot - Liquidity-flow snapshot over accumulated book events.
- Liquidity
Flow Tracker - Allocation-free liquidity-flow tracker.
- Market
Quality Snapshot - Market-quality and transaction-cost snapshot for one trade/quote pair.
- Market
Quality Tracker - Market-quality tracker retaining the latest quote.
- Ohlc
Volatility Estimator - Deterministic OHLC volatility estimator.
- Ohlc
Volatility Input - OHLC volatility estimator input.
- Ohlc
Volatility Snapshot - OHLC volatility estimator snapshot.
- Option
Flow Sample - Option flow sample.
- Option
Flow Snapshot - Option flow snapshot.
- Option
Flow Tracker - Cumulative option flow tracker.
- Pattern
Detail Analyzer - Deterministic detailed pattern-risk analyzer.
- Pattern
Detail Config - Detailed pattern-risk configuration.
- Pattern
Detail Input - Detailed pattern-risk input over a bounded observation window.
- Pattern
Detail Snapshot - Detailed pattern-risk snapshot.
- Pattern
Risk Classifier - Deterministic pattern-risk classifier.
- Pattern
Risk Config - Pattern-risk classifier thresholds.
- Pattern
Risk Input - Pattern-risk input over a bounded observation window.
- Pattern
Risk Liquidity - Pattern-risk liquidity summary.
- Pattern
Risk Snapshot - Pattern-risk snapshot.
- Queue
Decision Analyzer - Deterministic queue decision analyzer.
- Queue
Decision Config - Queue decision thresholds.
- Queue
Decision Input - Queue decision economics and replacement context.
- Queue
Decision Snapshot - Queue decision snapshot.
- Queue
Fill Config - Queue/fill probability configuration.
- Queue
Fill Snapshot - Passive fill probability snapshot.
- Queue
Fill Tracker - Queue/fill probability tracker.
- Queue
Fill Update - Queue update at the local order price.
- Queue
Position Estimate - Passive order queue estimate.
- Quote
Context - Best bid/ask context used by market-quality analytics.
- Regime
Classifier - Threshold-based market regime classifier.
- Regime
Input - Regime classifier input.
- Regime
Snapshot - Regime snapshot.
- Replay
Quality Analyzer - Deterministic replay-quality report analyzer.
- Replay
Quality Config - Replay-quality report thresholds.
- Replay
Quality Report - Replay-quality report derived from feed-quality counters.
- Resiliency
Config - Liquidity resiliency thresholds.
- Resiliency
Sample - Liquidity resiliency sample.
- Resiliency
Snapshot - Liquidity resiliency snapshot.
- Resiliency
Tracker - Threshold-based liquidity resiliency tracker.
- Toxicity
Analyzer - Deterministic toxicity/adverse-selection analyzer.
- Toxicity
Config - Toxicity/adverse-selection thresholds.
- Toxicity
Input - Toxicity/adverse-selection observation.
- Toxicity
Snapshot - Toxicity/adverse-selection risk snapshot.
- Trade
Context - Trade context aligned to a quote.
- Venue
Route Event - Venue route analytics event.
- Venue
Route Quality Analyzer - Deterministic venue route quality analyzer.
- Venue
Route Quality Config - Venue route quality thresholds.
- Venue
Route Quality Input - Venue route quality input.
- Venue
Route Quality Snapshot - Venue route quality snapshot.
- Venue
Route Snapshot - Venue route analytics snapshot.
- Venue
Route Tracker - Venue route analytics tracker.
- Volatility
Seasonality Snapshot - Intraday volatility seasonality bucket snapshot.
- Volatility
Seasonality Tracker - Fixed-bucket intraday volatility seasonality tracker.
- Volatility
Signature Estimator - Borrowed volatility signature estimator.
- Volatility
Signature Snapshot - Volatility signature point over borrowed returns.
- Volatility
Snapshot - Rolling volatility/noise snapshot.
- Volatility
Tracker - Fixed-window volatility tracker.
- Vpin
Snapshot - VPIN-style toxicity snapshot.
- Vpin
Tracker - Fixed-capacity VPIN-style bucket tracker.
Enums§
- Analytics
Error - Advanced analytics error.
- Feature
Quality - Per-feature extraction quality.
- Feature
Unit - Feature value unit.
- Liquidity
Regime Kind - Liquidity regime label.
- Missing
Value Policy - Missing-feature fill policy.
- Option
Kind - Option contract kind.
- Queue
Update Kind - Queue update kind.
- Regime
Kind - Market regime classification.
- Session
Regime Kind - Session phase regime label.
- Spread
Regime Kind - Spread regime label.
- Trend
Regime Kind - Trend/range/chop regime label.
- Venue
Route Event Kind - Venue route event kind.
Traits§
- Feature
Extractor - Feature extractor contract.
Type Aliases§
- Feature
Registry - Fixed-capacity feature registry alias.