Prediction skill only — nothing is bought or sold, real or simulated.
Claude calls UP/DOWN vs a coin-flip control; accuracy is scored against actual prices.
Pass / Fail — prediction skill, nothing else
…
Running accuracy (%) — resolved predictions
■ Claude ■ Classical math
(OU 1930 / variance-ratio 1988 / EMA) ■ Random control
· dashed line = 50% coin flip
Cumulative hypothetical return (%, frictionless)
Sum of signed moves if each call were followed with a fixed stake — an
upper bound; real trading costs would subtract ~2-3% per round trip.
Capital growth — ₹2,000 ($22.99) compounded through every resolved call
■ Claude ■ Classical math
■ Random control · dashed line = starting capital ·
frictionless (no fees/slippage) — an upper bound on what following each arm would have grown to.
Kelly-sized capital — betting only when a trailing edge exists
Half-Kelly fraction from each arm's trailing 30-call win rate (Kelly 1956),
capped at 25% of capital, zero until 10 outcomes exist. A flat line means Kelly's verdict is
"no edge — don't bet". This is the fastest honest compounding possible for whatever edge is real.
Calibration — does "60% confident" mean 60%? (Brier 1950)
Uninformative baseline
0.250
Lower Brier = better. Rows compare stated confidence with actual hit rate —
calibrated confidence is what makes Kelly sizing valid.
Measured earn-rate — what each arm would generate in a real up/down market (1% fee, half-Kelly)
Computed from each arm's last ≤200 scored calls at its live call rate.
"Bankroll for $1/min" inverts your target: the capital needed at CURRENT measured skill to
earn $60/hour. Below-breakeven skill = no bankroll size works; the fix is skill, not size.
Live hot board — best coin right now
Re-ranked every 5 seconds from raw feed ticks (the finest resolution public
data allows): live score = recent movement × tick persistence − round-trip cost − shallow-pool
penalty. This is the analyzer's recommendation of what's most active/tradable this moment;
the forecaster sees the same numbers.
Token catalog — trending candidates ranked by metrics
EvoML lab notebook — self-experiments, one generation every 30 min
Each row is one tournament: the champion genome (model kind, sensory
chromosome size, invented genes, call threshold, self-mutation rate) and its purged-holdout
score. Invented genes are expressions the model built from its own inputs and kept because
the lineage carrying them survived.
Claude's evolving playbook — self-written lessons, updated every 30 min
no playbook yet — written after 20 resolved calls
Latest Claude prediction (verbatim)
—