Glossary

AI Trading Glossary

The AI, trading, and market terms that actually matter in 2026 \u2014 defined in plain English, with deeper-dive links where it helps.

AI

Pattern Recognition
A machine learning approach that identifies recurring formations in price or volume data and matches them to historical analogs to forecast forward behavior. Core of Quanta’s Time Machine engine. Learn more
Dynamic Time Warping (DTW)
A similarity algorithm that compares two time-series sequences allowing for non-linear stretching. Used by Quanta to match current chart patterns against millions of historical analogs even when the timing differs.
Calibration
A measure of how well a model’s predicted probabilities match observed outcomes. A well-calibrated 70% bullish call should be right 70% of the time, not 50% or 95%. Tracked via Expected Calibration Error (ECE). Learn more
Expected Calibration Error (ECE)
The weighted average gap between predicted probabilities and actual outcome rates. Quanta’s target is ECE ≤ 0.02 on out-of-sample data.
Walk-Forward Validation
A backtesting method that trains a model on a rolling historical window and tests on the immediately following period, repeatedly. Prevents the overfitting that plagues simple in-sample backtests. Learn more
Regime Detection
AI-driven classification of the current market environment (trending, mean-reverting, high-vol, low-vol, etc.) so trading rules can adapt. The single most impactful AI feature for portfolio risk control. Learn more
Feature Vector
A numerical fingerprint of a stock or moment in time, built from dozens of indicators (RSI, MACD, volume profile, breadth, etc.). Models compare feature vectors, not raw charts.
AI Copilot
A conversational AI assistant trained on market data that answers research questions, explains signals, and suggests trades. Quanta’s Copilot is built for stock and crypto analysis specifically. Learn more

Trading

Sharpe Ratio
Risk-adjusted return: average excess return divided by standard deviation of returns. A Sharpe above 1.0 is good, above 2.0 is excellent. Quanta’s Proof Fund Sharpe is published on the track record page. Learn more
Sortino Ratio
Like Sharpe but penalizes only downside volatility. Often a more honest measure for strategies with asymmetric returns.
Drawdown
The percentage decline from a peak to a trough in portfolio value. Max drawdown is the worst peak-to-trough drop in the strategy’s history.
Position Sizing
The process of deciding how much capital to allocate per trade. AI sizing adjusts for setup quality, current volatility regime, and correlation to existing positions. Learn more
Portfolio Heat
Total at-risk capital across all open positions, weighted by correlation. Quanta enforces a configurable max heat (typically 6–8% of equity).
ATR (Average True Range)
A measure of price volatility over a lookback window. Used to set stop distances that adapt to the current vol regime, instead of arbitrary fixed percentages.
Backtest
Simulating a trading strategy against historical data to estimate forward performance. Reliable backtests use walk-forward validation, realistic slippage, and survivor-bias-free data. Learn more
Slippage
The difference between the expected fill price and the actual fill price. Real-world strategies lose 10–50bps to slippage that backtests usually ignore.

Patterns

Cup and Handle
A bullish continuation pattern resembling a teacup: a rounded bottom (cup) followed by a slight downward consolidation (handle), then a breakout. AI ranks cup-and-handle setups by depth, duration, and volume profile.
Bull Flag
A short consolidation against the prior trend, forming a flag shape. High-probability continuation setup when paired with rising relative strength.
Head and Shoulders
A reversal pattern with three peaks: a higher middle (head) flanked by two lower peaks (shoulders). Inverse pattern signals a bottoming process.
Breakout
Price moving decisively above resistance (or below support) on expanded volume. AI filters breakouts by historical follow-through rate for similar setups.
Mean Reversion
A class of strategies that bet on price returning to a statistical mean after a stretch. Works in chop regimes; loses badly in trends. Regime detection is essential.

Market Structure

Implied Volatility (IV)
The market’s forward-looking estimate of how much a stock will move, extracted from options prices. AI tools compare IV to historical realized volatility to find mispriced setups. Learn more
Realized Volatility
The actual standard deviation of returns over a historical window. The realized-vs-implied differential is one of the highest-edge inputs for options strategies.
Unusual Options Activity (UOA)
Options trades that are large or unusual relative to the contract’s normal volume. Often (but not always) a signal that informed money is positioning.
Order Flow
The sequence of buy and sell orders hitting the market. AI-ranked order flow filters out hedging and noise to surface the trades that actually move price.
Market Breadth
The percentage of stocks participating in a move (e.g., percent above their 50-day MA). A market rally with poor breadth is fragile; one with broad breadth is durable.

Crypto

On-Chain Data
Blockchain-derived metrics like exchange flows, stablecoin supply, miner reserves, and large-holder concentration. AI fuses on-chain with price for stronger crypto signals. Learn more
Funding Rate
The periodic payment between long and short holders of perpetual crypto futures, designed to anchor the contract to spot. Extreme funding rates flag positioning extremes.
Basis
The price difference between a futures contract and the underlying spot asset. Crypto basis trading was a major retail edge in 2021; mostly arbitraged away in 2026.
Liquidation
Forced closure of a leveraged position when margin is exhausted. Heat maps of pending liquidations are a useful AI input for short-term mean-reversion plays.

Quanta

Time Machine
Quanta’s pattern-matching engine that compares the current setup on any ticker against 5M+ historical analogs and shows the forward return distribution. Learn more
Proof Fund
Quanta’s public paper portfolio used to demonstrate live performance. Every signal is timestamped, every fill recorded at then-current market prices. No cherry-picking. Learn more
Daily Signals
The morning feed of high-conviction setups across stocks and crypto. Filterable by direction, holding period, sector, and confidence score. Learn more

Ready to put these to work?

Quanta AI applies every concept on this page across 3,000 stocks and 250+ crypto pairs \u2014 free to start, no credit card required.

Start free Full learning hubCompare platforms