Quantitative Analysis Suite

QuantTools

Select any asset from the full market universe — the AI auto-configures every model parameter from live data. Choose which tools to include and hit Run.

          Asset — Synced with Live Market Data
        

Select Models to Run

Select an asset above — AI will auto-configure all models from live data.

Seven Institutional Models

⟳

Monte Carlo

Equity curve simulation across thousands of paths

Risk · Ruin · Drawdown

GARCH Model

Conditional volatility clustering and forecast

Vol · Persistence · α+β

∕

Regression Channel

Linear trend with dynamic price bands

R² · Slope · Bands

◉

Neural Network

LSTM sequence model for price prediction

LSTM · MAE · Direction

≈

ARIMA Model

Time series forecast with confidence intervals

AIC · BIC · CI Bands

◈

HMM Regimes

Hidden Markov Model regime state detection

Bull · Neutral · Bear

∿

Kalman Filter

Optimal noise-removal for trend extraction

SNR · Lag · Q/R Ratio

⟳

MONTE CARLO SIMULATION

Equity curve · Risk of ruin · Drawdown distribution

Select an asset above — AI derives win rate, R:R and risk from live volatility.

Asset—

Win Rate—

R:R—

Trades—

Initial Balance ($)

Simulations

Simulating equity paths...

—

Mean Final

—

Median

—

Avg Max Drawdown

—

Risk of Ruin

—

Bear Case (10th %)

—

Base Case (50th %)

—

Bull Case (90th %)

—

Equity Curve Fan — All Simulated Paths

Strategy Viability

—

Risk Assessment

—

Actionable Advice

—

GARCH VOLATILITY MODEL

Conditional heteroskedasticity · Persistence · Vol clustering

Select an asset — model & horizon auto-selected from volatility regime.

Asset—

Model—

Horizon—

Estimating parameters...

—

Omega (ω)

Long-run variance

—

Alpha (α)

ARCH effect

—

Beta (β)

GARCH effect

—

Persistence

—

Annualised Volatility

—

Half-life of Shock

—

Vol Trend (forecast)

—

Vol Regime

—

Historical Conditional Volatility + Forecast

Persistence Interpretation

—

Vol Regime & Forecast

—

Position Sizing Advice

—

∕

REGRESSION CHANNEL

Price trend · R² fit · Dynamic support & resistance bands

Select an asset — regression type and band width optimised from price history.

Asset—

Type—

σ Band—

Horizon—

Fitting regression...

—

Slope

—

R² Fit

—

Trend Direction

—

Current Position

—

Price · Regression Line · Bands · Forecast

Trend Strength & Direction

—

Channel Position & Mean Reversion

—

Entry Logic & Targets

—

◉

NEURAL NETWORK PREDICTION

Deep learning sequence model · Price forecast · Confidence scoring

Select an asset — architecture and sequence length chosen by AI from data density.

Asset—

Architecture—

Seq Len—

Horizon—

Simulating model inference...

—

Confidence: —

—

—

Direction Acc.

Out-of-sample

—

MAE

Mean abs. error

—

RMSE

Root mean sq.

—

Predicted Move

—

Historical Price · Model Prediction

Model Reliability

—

Signal Interpretation

—

Risk & Limitations

—

≈

ARIMA TIME SERIES MODEL

Autoregressive integrated moving average · Confidence intervals

Select an asset — p, d, q orders auto-estimated via AIC on live closes.

Asset—

Order p,d,q—

Horizon—

Estimating ARIMA parameters...

—

AIC

Model fit criterion

—

BIC

Penalised fit

—

Forecast Dir.

—

Reliability

—

Historical · Forecast · 95% Confidence Bands

Model Fit Quality

—

Forecast & Reliability

—

Trading Application & Limits

—

◈

HMM REGIME DETECTION

Hidden Markov Model · Market state classification · Transition matrix

Asset

Number of States

Fitting Hidden Markov Model...

Return Sequence · Regime Coloring

Current Regime

—

Regime Stability

—

Optimal Strategy

—

∿

KALMAN FILTER

Optimal Bayesian filter · Noise removal · Trend extraction

Select an asset — Q/R noise ratio calibrated from live return variance.

Asset—

Model—

Q—

R—

Filtering signal...

—

Signal / Noise

Higher = cleaner

—

Filter Lag

Bars delayed

—

Trend Direction

—

Market State

—

Raw Price · Filtered Signal · Forecast

Signal Quality

—

Trending vs Choppy

—

Entry Logic

—

How to Build a Proper Quant Analysis

Identify the Regime

Start by understanding the current market state — trending, ranging, or transitioning. This determines which other tools are relevant.

HMM Regimes Kalman Filter

Assess Volatility

Before sizing any position, understand the current vol regime and forecast. This drives stop placement and position sizing.

GARCH Model

Find the Trend & Target

With regime and vol confirmed, identify trend direction, entry zone, and price target using regression or time-series models.

Regression Channel ARIMA Neural Network

Validate Risk Parameters

Before executing, simulate your strategy parameters to ensure the risk of ruin and drawdown profile are acceptable.

Monte Carlo

Tool	When to Use	Key Inputs	What It Tells You	Combine With
Monte Carlo	Before going live with a new strategy. Use to stress-test parameters before real capital.	Win rate, R:R ratio, risk per trade, number of trades	Probability of ruin, expected drawdown, realistic P&L range across scenarios	GARCH for vol-adjusted sizing
GARCH Model	Anytime before sizing a position or setting a stop loss. Always check vol first.	Asset symbol, model type (GARCH/EGARCH), forecast horizon	Current conditional volatility, persistence of shocks, vol regime (low/moderate/high)	HMM for regime context · Monte Carlo for sizing
Regression Channel	Trending markets only. Use R² to confirm a trend exists before applying.	Asset, band width (σ), forecast horizon	Trend direction and strength, overbought/oversold vs the channel, price target	GARCH to set band width · Neural Net for directional confirmation
Neural Network	Use as a directional signal confirmation — never as the sole reason to trade.	Architecture (LSTM/GRU), sequence length, forecast horizon, features	Predicted direction, confidence level, MAE/RMSE accuracy metrics	Regression for structural levels · HMM for regime validity
ARIMA Model	Short-horizon forecasting on liquid, stationary assets. Best for mean-reverting markets.	p, d, q parameters, forecast horizon	Point forecast with confidence interval, model fit (AIC/BIC), forecast reliability	Neural Net for non-linear patterns · Kalman to pre-smooth
HMM Regimes	First step of any analysis. Determines which other tools are applicable.	Asset (select from live prices), number of states (2–4)	Current market regime, stability score, regime probability distribution	Use output to decide: Bull → trend tools · Bear → mean-reversion · Neutral → wait
Kalman Filter	Noisy markets and high-frequency data. Pre-process before other models.	Q (process noise), R (measurement noise), model type	Clean trend signal, signal-to-noise ratio, market trending vs choppy classification	Regression on filtered signal · ARIMA on residuals

Recommended Tool Combinations

Trend Trade Setup

HMM → GARCH → Regression → Monte Carlo

Confirm bull regime, check vol is moderate (not extreme), find channel entry, validate risk parameters before sizing.

Mean Reversion Setup

HMM → Kalman → ARIMA → Monte Carlo

Confirm neutral/ranging regime, extract clean signal, forecast the reversion target, stress-test position sizing.

Volatility Breakout Setup

GARCH → HMM → Neural Net → Regression

Identify vol compression, confirm regime transition forming, get directional signal, find breakout target in channel.

Strategy Validation

Monte Carlo → GARCH → HMM

Run simulations with realistic win rate and R:R, adjust position size for current vol, check if regime supports the strategy.

The Future of
Market
Intelligence

MarketIntelligence

QuantTools

Track. Analyse. Improve.

The Future of MarketIntelligence

MarketIntelligence

QuantTools

Track. Analyse. Improve.

The Future of
Market
Intelligence