ChatPredict

← results overview

The combo finder — and why you can’t trust it

This searches every slice of the data for the best-looking edge. It’s a hypothesis generator, not a verdict — and here’s the honest math on why.

slices tested850
“significant” by luck alone~42at p<0.05
honest thresholdp<0.00006Bonferroni
slices that survive it0

Testing 850 slices, pure chance throws up ~42 that look “significant” at the usual p<0.05. So a single good p means nothing. Correcting for all the tries (Bonferroni), the bar is p<0.00006, and 0 slices clear it. Every row below is a hypothesis to test on fresh data, not a proven edge.

Most significant slices (min 50 trades)

slicetradeshit ratereturn/tradepsurvives?
gpt-4.1-nano + short + Large21863.3%+0.78%0.0001
gpt-4.1-nano + short + morning + Large8670.9%+1.38%0.0001
gpt-4.1-nano + short + Large + no spam19863.6%+0.74%0.0001
gpt-4o-mini + short + afternoon + Large + split13933.8%-1.50%0.0001
gpt-4.1-nano + short + Large + all agree18063.9%+0.81%0.0002
gpt-4o-mini + short + Large + all agree18063.9%+0.81%0.0002
consensus + short + Large + all agree18063.9%+0.81%0.0002
gpt-4.1-nano + short + morning + Large + all agree7171.8%+1.47%0.0002
gpt-4o-mini + short + morning + Large + all agree7171.8%+1.47%0.0002
consensus + short + morning + Large + all agree7171.8%+1.47%0.0002
gpt-4o-mini + afternoon + Large + split33339.9%-0.76%0.0002
gpt-4.1-nano + short + morning + Large + no spam7671.1%+1.43%0.0002
gpt-4o-mini + short + afternoon + Large + split + no spam13234.1%-1.34%0.0003
consensus + short + afternoon + Large + split12733.9%-1.49%0.0003
gpt-4.1-nano + short + Large + all agree + no spam16264.2%+0.83%0.0003

Highest return/trade — the microcap noise trap

These look spectacular but are tiny, illiquid slices whose p-values say "noise."

slicetradeshit ratereturn/tradep
gpt-4o-mini + short + Unknown + no spam7153.5%+2.79%0.553
consensus + short + Unknown + no spam6552.3%+2.46%0.710
gpt-4o-mini + short + Unknown8552.9%+2.33%0.588
gpt-4o-mini + short + Unknown + split5154.9%+2.23%0.484
consensus + short + Unknown7951.9%+2.02%0.736
gpt-4o-mini + morning + Unknown + split5060.0%+1.89%0.157
gpt-4o-mini + Unknown + split + no spam10950.5%+1.83%0.924
gpt-4o-mini + Unknown + split11950.4%+1.67%0.927
consensus + morning + Unknown + split5060.0%+1.62%0.157
gpt-4.1-nano + short + morning + Large + all agree + no spam6172.1%+1.55%0.001