← Back to Blog

ML Prediction

Which crypto coins can a simple ML model actually predict? (fresh run)

Auto-generated by Gordon Lab from a real backtest — published as a draft for review, not live.

Which crypto coins can a simple ML model actually predict? (fresh run)

The question: Re-running the 25-coin XGBoost direction study on the latest data — how many coins still beat a coin-flip out-of-sample?

What the data said

'ONDO' leads on auc: +0.542

Full results

group metric
ONDO 0.5416
ADA 0.5363
TRUMP 0.5189
AVAX 0.5186
CRV 0.5182
SOL 0.515
XRP 0.5146
PEPE 0.5141
ETH 0.513
ARB 0.5121
DOGE 0.5115
LINK 0.5112
RENDER 0.5107
BTC 0.5092
UNI 0.5091

Generated by Gordon Lab from a real backtest. Method + caveats live in the harness; this is research, not advice — and the losing runs are shown too.