Two decades of pattern
recognition research.
One question worth answering.
What happened the last time this stock looked like this? Every trader asks it. Almost nobody can actually answer it. Konseki was built to close that gap — pre-computed, updated daily, for every symbol in coverage.
Background
Songyang Guo, founder of Konseki, has spent two decades at the intersection of market research and quantitative trading. His interest in market pattern recognition began in 2006 during PhD research in Econometrics at Monash University, where his work focused on stock market similarity and computational finance — the mathematical foundations of what Konseki does today. In 2008, while still completing his research, he joined Argus Capital Management as a quantitative trader, applying that research directly in live markets. He discontinued the programme in 2011 as his trading career accelerated.
He later founded Enigma Capital Management, leading the research and development of pattern-recognition trading systems. Across his hedge fund career, Songyang managed more than US$120 million across equities and global futures markets.
Over the past decade, Songyang has worked as a software engineer and technology entrepreneur while continuing to trade actively using proprietary pattern-recognition models. The gap he kept running into — that answering "what happened last time this setup appeared?" takes serious data and compute most traders will never have — became the product idea behind Konseki.
Monash University
Argus Capital Management
Enigma Capital Management
Technology Entrepreneur
Why Konseki
The problem that led to Konseki is simple: you can see the setup, but you can't see its track record. Charting tools, flow alerts, indicator marketplaces and trading Discords are all built to help you spot a pattern faster. None of them tell you what actually happened the last dozen times a stock looked like this — how often it worked, how big the move was, how far it went against you first.
Answering that properly is not a quick lookup. Finding structurally similar setups means searching decades of daily history across hundreds of symbols, then measuring what followed each one. Even a small group of symbols can take hours to compute. It is not something you can run in the moment you actually need it — which is precisely when you need it.
So in practice, almost nobody does it. Traders fall back on instinct, a vague sense of the odds, and whatever the last few similar-looking charts happened to do. The evidence exists — it's sitting in decades of market history — it's just never been within reach at the moment a decision gets made.
The fix is to stop trying to compute it on demand. Konseki runs the whole thing every market close, ahead of time, so the answer is already waiting when you type a ticker — no scripts, no spreadsheets, no waiting.
The engine runs every trading day across a growing universe of global equities †, with coverage expanding continuously. 8 lookback windows. 4 forward windows. Win rates, outcome distributions, match quality scores, how far price moved against the setup before it resolved — plus a plain-language read on every result, so you don't have to interpret a wall of numbers.
Every day's output is stored as a permanent, immutable snapshot — exactly what the engine returned on that day, not a reconstruction after the fact. It means the read you get is the read that existed at the time, and the data you cite today is the same data you'll get tomorrow.
You spot the setup. We show you the track record.
The methodology is publicly documented. The free tier exists so you can judge the data quality yourself before paying for anything. The product stands on the evidence — not on claims about it.
† Symbol coverage expands automatically as Konseki grows — existing subscribers get expanded coverage at no extra cost.
"Every trader already reasons from patterns. The gap was never the instinct — it was never being able to check it against what actually happened."
The gap Konseki was built to close.
"What happened the last time markets looked like this?"
The question Konseki was built to answer — for every symbol in coverage, every trading day.