Backtest

I’ll skip the theory. Here’s what actually happened. The Problem I was building a crypto price prediction model for SOL, ETH, and BTC perpetual futures. The plan was simple: train a Transformer on 70 features, get a good signal, trade it live. Three weeks of training later: SOL Transformer v3b: train_acc = 69.3%, val_acc = 54.1%, gap = 15.2% ETH Transformer v3b: train_acc = 78.6%, val_acc = 55.9%, gap = 22.7% The gap between training and validation accuracy was 15-22%. Classic overfitting. The model was memorizing patterns, not learning them. ...

Fear & Greed = 11. Bitcoin at $62,873. Here’s what the data shows. February 5, 2026. Fear & Greed Index: 11. Extreme Fear. Most people were selling. Bitcoin was at $62,873. If you had bought a 10% out-of-the-money call option that day — 7 days later Bitcoin hit $70,290. An 11.7% move. That option returned +4,991%. This Isn’t Luck. It’s a System. I backtested 400 days of data. Strategy: when Fear & Greed < 20 + large liquidation event happen simultaneously, buy 10% OTM options, hold 7 days. ...