Research beyond
the backtest.
Markets reward an edge. We start by asking whether the evidence survives.
OPEN METHODS / PRIVATE DISCOVERIES / NO HYPE
Evidence, not a winning curve.
A method preview. Not investment performance.Data provenance before a performance claim.
Costs, bias and failed trials stay visible.
Risk tools with clearly stated limits.
Start with a better question.
The missing trials change the story.
The best curve is less informative when you do not know how many curves were tried.
A market is more than its price history.
Korean equities are a distinct research track, not a renamed crypto dataset.
The cost is part of the strategy.
A small gross edge can disappear between a signal and an executable order.
The experiments behind the methods.
Stockback research archive
64 historical Korean equity research records. Read the experiment design, actual report and verdict together.
Coinback research archive
E-01 through E-25 and the surrounding research record, including execution-cost, funding, maker replay and liquidation-data diagnostics.
The record behind the research.
Original Korean research records from Stockback and Coinback, preserved with source hashes and explicit historical context.
Know the risk
before the trade.
Practical tools that run in your browser. No trading account connection. No uploaded trade history.
Open the toolkit ↗Evidence has a structure.
Evidence has a chain of custody.
Every result should tell you what was known, what was assumed, and what remains untested.
Choose the rules before the challenge.
A profitable strategy can still be incompatible with an evaluation rulebook.
A lab, not a promise.
QuantProp exists to make the difference between a compelling backtest and credible evidence easier to see.
A lab, not a promise.
See exactly how we separate exploration, verification and publication.