Quantitative Signals & Scoring

Adverse Selection Indicator

A market microstructure metric that quantifies the probability that a trade counterparty possesses informational advantage, derived from the asymmetric pricing impact of buy versus sell orders.

Alpha Decay Trajectory

The measurable pattern and speed at which a trading signal's predictive edge diminishes over time following its initial generation or publication.

Backtest Universe Alignment

The process of ensuring that the security universe used in historical backtesting matches the investment universe available at each historical date, preventing look-ahead bias and survivorship bias in signal performance evaluation.

Cluster signal

A pattern in which several distinct insiders at the same company buy within a short window, which historically predicts stronger forward returns than any single buy.

Coefficient of Variation Filter

A statistical screening mechanism that ranks or excludes trading signals based on the ratio of standard deviation to mean return, isolating strategies with consistent risk-adjusted performance across market regimes.

Composite Conviction Index

A quantitative scoring metric that aggregates multiple insider-trading signals, behavioral indicators, and market microstructure factors into a single normalized conviction signal, weighted by signal persistence and predictive power.

Conditional Expectancy Score

A quantitative metric that estimates the expected return or probability-weighted outcome of a security conditional on observed insider trading activity, regulatory filings, or market microstructure signals at a specific point in time.

Conviction Score Clustering

A quantitative technique that groups insider trading signals and behavioral indicators by strength of conviction to identify cohesive, high-confidence trading opportunities while filtering noise.

Cross-Sectional Factor Exposure

The relative loading or sensitivity of a security to systematic risk factors measured at a point in time across a universe of comparable peers.

Crowding Intensity Metric

A quantitative measure of the degree to which a trading signal or strategy is crowded among market participants, indicating elevated competition and reduced alpha potential.

Drawdown Recovery Speed

The rate at which a portfolio or signal recovers to its previous peak after experiencing a drawdown, measured as the number of periods or time required to restore equity above the high-water mark.

Earnings Surprise Momentum

A quantitative signal measuring the directional persistence and magnitude of price momentum following positive or negative earnings surprises, used to score insider trading conviction and market inefficiency.

Edge Half-Life Calculation

A quantitative measure of the time period required for an insider trading signal or informational edge to decay to half its original predictive power or alpha generation capacity.

Factor Loading Stability

The consistency and persistence of a signal's exposure to systematic risk factors over successive time periods, measured to assess whether predictive power derives from stable structural relationships or transient market conditions.

Factor Orthogonalization

A statistical technique that removes correlation between scoring factors to isolate their independent explanatory power and prevent multicollinearity bias in insider-trading signal generation.

Feature Importance Weighting

A quantitative technique that assigns differential weights to input variables or signals in a predictive model based on their relative contribution to explaining or predicting insider trading activity and market movements.

Forward Testing Slippage

The difference between expected signal performance observed in backtesting and actual execution costs, market impact, and liquidity constraints encountered during live or out-of-sample trading.

Fundamental Momentum Divergence

A quantitative signal that identifies asymmetric price-to-value misalignment, where short-term momentum trajectories diverge from longer-term fundamental growth rates, flagging potential mean-reversion or sustained mispricing opportunities for insider-correlated positions.

Hedging Ratio Optimization

The dynamic calibration of position-level or portfolio-level hedge ratios to minimize signal drawdown and volatility while preserving alpha capture in insider-activity-driven strategies.

Information Coefficient

A statistical measure of the correlation between a signal's predictions and actual subsequent asset returns, normalized to account for forecast accuracy and used to validate the predictive power of insider trading indicators and quant scoring models.

Information Decay Coefficient

A quantitative measure of the rate at which a signal loses predictive power or relevance over time following the initial event or data release.

Insider Activity Concentration

A quantitative metric measuring the degree to which insider trading activity is concentrated among a small number of filers or clustered within specific time windows, used to assess the uniformity, signal strength, and potential coordination of insiders.

Insider track-record score

A factor rewarding insiders whose past disclosed trades were, on average, well-timed, measured by the forward return of their prior buys.

Latency-Adjusted Ranking

A scoring methodology that penalizes or reranks signals based on the time delay between signal detection and market-actionable information availability, correcting for execution and information dissemination lag.

Liquidity-Adjusted Alpha

A risk-adjusted excess return metric that penalizes alpha generation for the cost and friction of trading illiquid positions, ensuring that apparent outperformance is achievable in practice.

Look-Ahead Bias

A backtesting error where a quant model uses information or data points that were not available at the decision time, artificially inflating historical performance and masking true signal quality.

Macro Regime Synchronization

The degree to which a trading signal or insider activity pattern aligns with the current macroeconomic regime (growth, stagflation, disinflation, recession) to assess predictive validity and reduce regime-dependent false positives.

Market Microstructure Signal

A quantitative indicator derived from order book dynamics, bid-ask spreads, volume patterns, and price impact that detects informed trading activity or unusual liquidity conditions preceding material price moves.

Mean Reversion Half-Life

The time period required for an anomalous price deviation to decay to half its initial magnitude, measured through exponential mean reversion dynamics.

Multi-Horizon Scoring

A quantitative framework that evaluates insider trading signals and market anomalies across multiple time horizons simultaneously, aggregating predictive strength at intraday, short-term, medium-term, and long-term intervals to produce a composite conviction score.

Normalization Z-Standardization

A statistical technique that transforms raw signal values into a standardized scale with mean zero and unit variance, enabling cross-sectional and temporal comparability of heterogeneous scoring inputs.

Percent of market cap

The value of an insider trade expressed as a fraction of the company's market capitalisation, a size-normalised measure of how meaningful the trade is.

Percentile Rank Distribution

A statistical method that assigns each signal or insider transaction a percentile rank relative to the cross-sectional distribution of all comparable observations, enabling normalized comparison of signal strength across heterogeneous assets and time periods.

Point-in-Time Normalization

A methodology that rescales raw insider trading or market signal metrics to a standardized distribution at each historical observation date, preventing look-ahead bias by using only information available at that precise moment.

Prediction Lift Coefficient

A normalized metric quantifying the incremental predictive power of a signal relative to a random or baseline model, expressed as the ratio of signal-driven outperformance to the baseline prediction error.

Probabilistic Ranking System

A quantitative framework that assigns probability-weighted scores to securities or trading signals based on Bayesian inference, machine learning predictions, or Monte Carlo simulations, enabling dynamic ranking of insider trading risk or signal strength.

Regime Detection Probability

The statistical likelihood that a quantitative signal correctly identifies a shift in market regime or insider trading behavior pattern, measured as the conditional probability that observed signal characteristics align with known regime markers.

Relative Value Score

A quantitative metric that ranks an asset's valuation relative to peers or historical norms, adjusting for sector, market cap, and fundamental factors to identify mispricings exploitable by insider trading activity correlation.

Repeat-buying (DCA) score

A factor rewarding an insider who adds to a position across several disclosures, treating sustained accumulation as stronger conviction than a one-off purchase.

Residual Strength Metric

A quantitative measure of abnormal price or volume momentum that persists after removing systematic market, sector, and factor-driven movements, commonly used to isolate insider trading signals from broad-based market trends.

Rolling Hit Rate

The percentage of profitable signal executions measured over a moving time window, used to assess signal quality and scorer reliability in real-time trading environments.

Sector momentum

The trailing return of a stock's sector index, used as a contextual factor: an insider buy is more potent when the sector itself is in an uptrend.

Sector-Neutral Factor Score

A quantitative signal that isolates the alpha contribution of a fundamental or behavioral factor by removing sector-level performance bias, enabling identification of stock-specific alpha independent of sector momentum or cyclicality.

Sentiment Reversal Propensity

A quantitative metric measuring the statistical likelihood that an extreme insider sentiment signal will reverse within a defined forward-looking period, adjusted for regime and conviction strength.

Sigma score

A composite 0 to 100 score that ranks an insider transaction by how predictive it is of forward returns, blending conviction, role seniority, cluster strength and timing into one number.

Signal Decay

The progressive loss of predictive power or statistical significance of an insider trading or market signal as time elapses following its initial detection.

Signal Persistence Metric

A quantitative measure of the tendency of an alpha signal to maintain predictive power and directional consistency across successive time periods, adjusted for market regime changes and decay dynamics.

Signal Turnover Efficiency

The ratio of net signal-driven trading profit to the total transaction costs incurred in executing positions based on that signal, measuring how much alpha a signal generates per unit of implementation friction.

Signal-to-Noise Ratio

A metric quantifying the strength of a predictive signal relative to random fluctuations or false positives in a quantitative scoring model.

Tail Risk Adjustment

A scoring modification that penalizes or reweights signals exhibiting disproportionate exposure to extreme market drawdowns or low-probability, high-impact adverse events.

Time Series Momentum Regime

A quantitative framework identifying periods when an asset's past returns predictably drive future price movements, enabling regime-conditional scoring adjustments for insider-trading and market-timing signals.

Transaction Cost Drag

The reduction in net signal returns caused by trading costs, including commissions, bid-ask spreads, market impact, and execution slippage, which erodes alpha and reduces the practical profitability of a quant or insider-activity strategy.

Volatility-Scaled Signal

A quantitative signal whose strength or weight is inversely adjusted by the realized or implied volatility of the underlying security to normalize conviction across varying market conditions.

Z-score

The number of standard deviations a value sits above or below the mean of its distribution.