Deep dives into AI trading, market analysis, and the future of DeFi.
Browse collections →Nothing found. Try a different query.
Crypto correlations are not constant — they spike toward 1 in every drawdown. DCC-GARCH models a time-varying correlation matrix, giving you dynamic hedge ratios for pairs trading and honest time-varying portfolio risk.
Plain GARCH(1,1) treats good and bad news the same and assumes Gaussian shocks. EGARCH, GJR-GARCH, and Student-t/skew-t innovations fix both — and give you honest VaR and Expected Shortfall for crypto.
How the GARCH(1,1) model captures volatility clustering in crypto, how to fit it by maximum likelihood with the arch library, and how to turn conditional-variance forecasts into position sizing and dynamic stops.
The capstone of the search-and-overfit arc, and it ends in a negative result — the correct one. A single-symbol dual-timeframe search on ETHUSDT found a config worth +16.35% out-of-sample and +2.62% on an untouched holdout; the Deflated Sharpe Ratio, accounting for ~37,000 trials, deflated it to 0.00. A cross-instrument pass over five majors (ETH/BTC/SOL/BNB/XRP, ~1.18M 1m bars each), selecting by median out-of-sample, kills it for good: dual DSR 0.24 / PBO 0.264, triple DSR 0.14 / PBO 0.327 — both fail the gates. The champion is profitable on 1 of 5 symbols and negative on the rest. This is what the anti-overfit apparatus is for: to stop you from shipping the best of noise as alpha.
Multi-timeframe backtests leak the future through a forming higher-timeframe bar whose final close does not exist yet. You cannot code-review your way to confidence — you have to test it. We reproduce the live bot's closed-bar rule exactly, then prove no leakage with a shifted-future probe: perturb every future bar and assert every past signal and trade is bitwise unchanged. 25/25 parity checks, and the probe has teeth.
The GPU's lead over CPU grows with batch size — 54.5x at one combo per call up to 359.6x at 61 on our multi-timeframe indicator precompute — because a small sweep cannot amortize kernel-launch and transfer overhead. We decompose a headline 167x into a 27x algorithmic win that also helps the CPU and a 6.2x hardware win, show the true GPU-vs-best-CPU lead is only 3.2x single-timeframe and 6.2x multi, and give a decision guide for how wide a sweep must be before a GPU is worth buying into.
Apple's Metal GPU has no float64. Port a vectorized backtest to it naively and the tempting prefix-sum WMA overflows fp32 — max relative error 211× — yet it still runs and returns plausible-looking numbers. The fix is not more precision; it is a different formulation: a direct windowed convolution, fp32-safe to 8×10⁻⁷ and 55.9× faster than single-thread numba. The trap, the arithmetic, and how to prove you didn't fall in.