Leptokurtic
Financial returns have fat tails. Crashes that Gaussian models call impossible happen regularly. This series assembles nine centuries of exchange-rate data, builds a crash-detection toolkit from 13 statistical methods, and tests whether tail hedging with options actually works.
Episodes
We assembled forex-centuries, an open dataset of exchange rates from 1106 to 2026 covering 240 countries from 13 sources. Fat tails are universal. Pegged currencies are the most dangerous. Every currency loses against gold.
We built fatcrash, a Rust+Python toolkit with 13 crash detection methods: LPPLS, DFA, EVT, Hill, Kappa, Hurst, GSADF, and more. Tested on 39 drawdowns across BTC, SPY, Gold, and 54 years of forex. DFA detects 82% of crashes. The combined detector reaches 79%.
We tested Spitznagel’s tail hedging strategy and AQR’s critique with 17 years of real SPY options data. AQR is correct about a strategy nobody runs. Spitznagel’s actual strategy, leveraged deep OTM puts, wins on every metric. Weekly rebalancing pushes Sharpe to 1.7. Macro signals are useless for timing.
This series is in progress, stay tuned!