Overview Bots Connect Binance Pricing
Research sandbox
Volatility forecast Risk tooling Jump analysis
These three run on generated data, not your account — they exist to show the analysis, not your results.
Overview, Bots and Connect show your own account. The sandbox pages above do not.
Your account

Overview

Loading your strategies…

Binance account

Checking…
RESEARCH SANDBOX — generated data, not your account. This volatility forecast runs on a synthetic price series so the analysis can be shown; none of these numbers describe your money.
Forecasts

JEPA-based predictions

MOCK — illustrative only, not live model output

The real JEPA latent-representation model validated an information coefficient of 0.13–0.44 for realized-volatility forecasting in backtest (see project notes) — direction forecasting was tested and refuted. This panel illustrates what a live version could show: a predicted-vs-realized volatility forecast per asset, and a current regime read. The lines below are generated from the synthetic series, not a live model.

Predicted vol regime
Predicted 30d vol (ann.)
Realized 30d vol (ann.)
Illustrative IC
mock, not the real backtest figure
RESEARCH SANDBOX — generated data, not your account. This risk tooling runs on a synthetic price series so the analysis can be shown; none of these numbers describe your money.
Risk

Risk management

Monte Carlo simulation

Geometric Brownian motion, parameters fit from the synthetic asset's own historical drift/volatility. Genuinely simulated client-side (not hardcoded) — change the inputs and re-run.

P5 (bear)
P50 (median)
P95 (bull)
Simulated VaR 95% (horizon)

Value at Risk

1-day VaR/CVaR computed two ways from the same synthetic return history: historical (empirical quantile) and parametric (assumes normal returns) — shown together because they typically disagree most exactly when it matters, in the tails.

Historical VaR
Historical CVaR
Parametric VaR (normal)
Parametric CVaR

Suggested additional metrics

Beyond VaR — these catch things VaR alone misses: how bad the average bad day is (CVaR, above), whether the distribution is fat-tailed (kurtosis), how concentrated the book is (Herfindahl), and downside-only risk-adjusted return (Sortino).

AssetSkewnessExcess KurtosisSharpeSortinoMax DD
Portfolio concentration (HHI)
0.20 = perfectly even across 5 assets; 1.0 = single-asset

Spillover: VAR(1) + impulse response

A reduced-form vector autoregression (1 lag) is fit by least squares on the 5-asset synthetic return history. Pick a "shock" asset and see how a 1-standard-deviation move propagates to the rest of the portfolio over the following periods. This is a genuine (if simplified) VAR/IRF calculation, not looked up — but it's a reduced-form shock, not a properly identified structural one (no Cholesky/sign-restriction ordering), so read direction and relative magnitude, not precise causal size.

RESEARCH SANDBOX — generated data, not your account. This jump analysis runs on a synthetic price series so the analysis can be shown; none of these numbers describe your money.
Volatility

Volatility analysis & jump detection

Rolling realized volatility (20d, annualized)

Price with flagged jump days

Jump analysis

Two methods, shown together: a simple threshold rule (flag a day if |return| exceeds 4× its trailing 20-day volatility — the red dots on the chart), and a realized-variance decomposition (Barndorff-Nielsen & Shephard bipower variation) that separates total variance into a continuous component and a jump component without needing a threshold at all.

Threshold jump days
Avg jump size
Realized variance (RV)
Jump share of variance (BNS)
RV − bipower variation, as % of RV