The daily regime brief is published each morning in the channel

Holding Bitcoin was never the hard part.
Knowing what the model says is.

Most people rode −75% to the bottom not because they were wrong — but because they had no structured quantitative framework for reading market conditions. Every morning we publish the model's regime classification and standardized exposure variable — rigorous, quantified research context. Subscribers independently decide what, if anything, to do with it.

No API keys. No custody. Cancel renewal at any time. General research, delivered to Telegram once a day.

The double wound

The same mistake, made twice

You didn't get hurt because you were wrong about Bitcoin. You got hurt because you held the same amount no matter what the market was doing. So you ate the full drawdown on the way down — and then, too burned to step back in, you watched most of the recovery happen without you. That's the part nobody says out loud: the crash and the missed rebound aren't two mistakes. They're the same mistake, made twice. Not a conviction problem. A sizing problem.

Buy & hold reality

−75% means three-quarters of it is gone

+300%
just to break even

is what you now need just to get back to even. Not to profit — to break even. That's years of waiting. Most people don't last. They capitulate within sight of the bottom.

The Vantegio approach

−11.2% is manageable, not a catastrophe

+13%
just to break even

is all a −11.2% drawdown requires to recover, compared with a +200% gain needed after a −66.7% drawdown. Smaller drawdowns have historically been easier to hold through — but past model behaviour does not guarantee future results.

Drawdowns are not symmetric. A loss of X needs a gain of X / (1 − X) to undo it — and that ratio explodes as the hole gets deeper. A smaller drawdown requires a smaller recovery. That asymmetry, compounded across cycles, is the thesis behind lower-exposure positioning — though the model cannot guarantee any specific future drawdown.
Schematic illustration — model vs buy-and-hold drawdown profile
BTC buy & hold Vantegio model
0% −25% −50% −75% BTC trough ≈ −75% model floor ≈ −11.2% (walk-forward) cycle I cycle II cycle III now
Illustrative shape of drawdown depth over the out-of-sample window. The model reduced exposure as corrections developed — historical model output, not a guarantee of future behaviour. Y-axis: percent below the prior equity peak.
Schematic illustration — model exposure variable through a stylised cycle
BTC price (stylised) Model exposure variable
100% 50% 0% cycle top capitulation ~90% — full expansion model reduced exposure accumulation bull / expansion distribution bear next expansion
The model's exposure variable is not fixed. Historically it rose toward ~90% in expansions, decreased ahead of regime transitions, and sat low through bear markets — then rebuilt. The ~36% figure is the historical average across all regimes. Past model behaviour is not a guarantee of future output.

Methodology

Three models. One number.

No single indicator survives every market. The ensemble combines three independent models watching different horizons, each checking the others — resolving to one standardized exposure variable, 0–100%.

Anchor
Macro
Macro cycle anchor

Reads where Bitcoin sits in its long-horizon cycle and suppresses false signals when the tape is just noise. The slow, steady hand.

Primary
Tactical
Tactical correction detector

The most influential model. Watches the tactical horizon and detects regime transitions as they develop — before the drawdown has fully materialised in historical data.

Veto
Risk-On / Risk-Off
Structural veto

Built specifically to disagree with the Tactical model when the evidence for a regime change is thin. When it contradicts, confidence drops and the model's exposure variable decreases. It exists to prevent overreaction.

The circuit-breaker

Models can be wrong. So there's a hard rule that overrides them: if Bitcoin's drawdown breaches a fixed threshold while the ensemble still reads Bull, the model's exposure variable is automatically halved — regardless of what any individual model says.

A seatbelt for the case where the data is lying and price is telling the truth.

Stress-tested & version-controlled

Every layer in the live model has been run through dedicated stress tests: synthetic worst-case paths, regime-transition shocks, liquidity-constrained periods. Model outputs, regime classifications, and confidence readings are archived daily — the historical record cannot be revised retroactively.

You're not trusting a screenshot. You're trusting a documented, version-controlled record.

Powered by a multi-source data pipeline covering on-chain, derivatives, and cross-asset feeds.


Why this is different

Built to survive scrutiny, not to pass a screenshot

Anyone can post a green curve. The question a serious person asks is how was it produced — and that's exactly where most signal services fall apart.

Most signal services
Vantegio
A backtest tuned to one hand-picked window
Multiple years of out-of-sample results, model frozen first
A single black box — "just trust us"
Three models, and you see every vote, every day
Built once, never changes again
A research pipeline that keeps adding validated layers
Only ever shows you the winning trades
We publish selected model results — including periods of underperformance

Performance

Performance comparison

Most services show you a backtest. We show selected summary results from two independent test periods: a nested walk-forward OOS where the model was frozen before the window opened, and a blind holdout the models had genuinely never touched. Both produced risk-adjusted results meaningfully above buy-and-hold.

Holdout 2025-01-01 to 2026-05-31 — current production model (net of 5bp execution cost)

This is the model currently supplied to subscribers. CAGR figures are annualised, not cumulative returns.

Metric Vantegio BTC B&H
CAGR +30.7% −16.3%
Max drawdown −16.4% −49.5%
Calmar ratio 1.87 −0.33
Sharpe ratio 1.21 −0.18

Nested walk-forward OOS 2022-01-01 to 2024-12-31 — current production model (net of 5bp execution cost)

This is the model currently supplied to subscribers. CAGR figures are annualised, not cumulative returns.

Metric Vantegio BTC B&H
CAGR +76.4% +25.6%
Max drawdown −11.2% −66.7%
Calmar ratio 6.83 0.38
Sharpe ratio 2.15 0.69
Avg. BTC exposure 36% 100%
Holdout verdict — blind test, 2025-26
+30.7%
vs −16.3%
Our CAGR vs Bitcoin's CAGR on data our models had genuinely never seen.

A blind holdout is the closest thing to a genuine out-of-sample test — the model was sealed before this period opened and has not been retouched since. It reduces, but does not eliminate, overfitting and selection bias. Bitcoin's annualised return was −16.3% over this period. The model's annualised CAGR was +30.7%. That's not a promise about the future. It's a record of what the model output was when it had no way to know what was coming. Past performance does not guarantee future results.

On the nested walk-forward OOS: model Calmar 6.83 vs 0.38 for buy-and-hold — 18× more return per unit of drawdown. Bitcoin's −66.7% crater requires a +200% recovery just to break even. The nested walk-forward max drawdown of −11.2% requires just +13%.

Skill, not beta

We tested whether the edge is just Bitcoin exposure in disguise: hold passive BTC at the model's own average exposure level, and compare. On the sealed holdout, that same-exposure passive book lost money (−4.9%) while the model made +30.7%, with a low beta to BTC (0.32–0.40) throughout both test windows.

The return isn't coming from being invested. It's coming from being invested at the right times.

Risk & tail profile

The de-risking shows up in the shape of the returns, not just the average: holdout return skew is +2.2, strongly right-tailed — the model captured 46% of Bitcoin's up moves but only 35% of its down moves. A 5,000-path Monte-Carlo simulation over a 17-month forward horizon puts the odds of a losing 17-month stretch at 5%.

Operating requirement

The edge is timing-sensitive: execute within ~2 hours of the daily signal. At +2h delay, the sealed holdout retains a Sharpe of 0.96 (of 1.13 at zero delay); a 4–6h delay roughly halves it.

This is a live execution discipline, not a backtest assumption — daily research is published on a fixed early schedule specifically so a prompt subscriber can act inside this window.

Methodology note. Nested walk-forward OOS: 2022-01-01 to 2024-12-31. Blind holdout: 2025-01-01 to 2026-05-31. All figures are model simulation results — they do not represent a live-managed account or subscriber returns. Model parameters were frozen before each window opened and were not adjusted within the window. Returns assume daily rebalancing at close price and are net of a 5bp all-in execution-cost assumption (trading fees and slippage combined); taxes are excluded. Cash earns 0% when BTC exposure is below 100%. CAGR is annualised from cumulative return over the stated period. Calmar = CAGR ÷ max drawdown. These figures reflect the model currently in production; any future research improvements will be labelled with their own version and date. A reproducible daily time series is available on request.
Risk disclosure. Vantegio publishes quantitative model outputs as general, non-personalised research — not financial advice. Cryptocurrency is a high-risk asset class — you may lose some or all of your capital. Past performance does not guarantee future results. You are solely responsible for your investment decisions. Mentions légales →

Active research

The model improves. You don't have to do anything.

This isn't a model built once and left to age. It's a living research engine: new analytical layers are tested continuously against the same strict holdout discipline. When one passes, it's integrated into the live output automatically — no migration, no re-subscription, no action on your part. The research you access next year will be more rigorous than today's.

How the research evolves

Already in production

The core regime ensemble has been running live since launch. A macro risk-appetite overlay has since passed the holdout gate and been folded in — a validated improvement, not a patch. This is the process in action.

The filter is the product

We have rejected more strategies than we have deployed. The ones that didn't survive a blind holdout — where the model had genuinely never seen that data — get archived, not shipped. You only ever see what earned its place.


Who's behind it

Two people. Two ways a signal can lie. Both covered.

A signal can fool you with bad statistics, or it can fool you with a pretty backtest that never survives real markets. We're built so that neither gets past us.

Q
Quant & AI
Quantitative researcher & AI engineer

Deep technical background in quantitative modelling and machine intelligence, applied specifically to crypto markets. Built the model architecture, the validation framework, and the research pipeline behind every number on this page. The kind of person who knows exactly why most "signals" are statistical artefacts — and engineered this system specifically so it wouldn't be one.

"Most signals look great on paper because they were fitted to the paper. We built the opposite: a system that has to earn its numbers on data it has never seen."
M
Markets
Professional FX & equities trader

Years of live trading experience across foreign-exchange and stock markets. Brings the practitioner's lens the math can't supply: which signals survive real execution, where models get punished by the way markets actually move, and what a drawdown feels like with real money on the line. The one who asks of every model — "would I genuinely have held this through 2022?"

"I've been on the wrong side of enough drawdowns to know the math doesn't matter if you can't hold the position. This is built for people who need to sleep."
There is no version of this model output we keep for ourselves. It is timestamped and distributed simultaneously to all subscribers. We do not trade in anticipation of subscriber activity and we do not accept payment from exchanges for model inclusion.

What you actually get

One research brief a day. Everything you need to form a view.

No dashboard to babysit. No charts to stare at. Every morning a concise research brief lands in a private Telegram channel — regime classification, the model's standardized exposure variable, confidence level, and the full model breakdown so you understand why the output changed.

  • Daily regime classification
    Bull / Expansion · Accumulation / Pre-Bull · Distribution / Risk-Off · Bear / Capitulation. Where the model places the current market environment.
  • Standardized exposure variable
    A quantified research variable, 0–100%, derived from the ensemble. It summarises the model's current regime assessment — subscribers independently decide what, if anything, to do with it.
  • Model state update
    When the regime classification changes, you get an immediate notification. Historically this happens roughly 55–115 times a year (about 80 on average) — call it weekly, not several times a day.
  • Full model breakdown
    What each of the three models voted, the confidence level, and whether the circuit-breaker is active. No black box — every reading is explained.
  • Exchange-independent research
    The model output is a standardized research variable — not tied to any platform. Subscribers independently decide whether and how to use it, on any venue they already use. We never touch your funds.
V
Vantegio · Regime Research
channel · research · historical output from 2019
📡 BTC Regime Update — 2026-06-17
Regime🟠 Distribution / Risk-Off
Exposure reading15%
Model stateUnchanged
Confidence80%
Circuit-breakerOff
Model breakdown
• Macro20%DISTRIBUTION
• Tactical20%DISTRIBUTION
• Veto0%BEAR
07:02


Pricing

€49/mo — research subscription.

Early subscriber pricing
Daily regime research · private channel
€49/ month
Subscribe now. Review the CGV for full subscription terms.
  • Daily regime classification and model exposure variable
  • Full three-model breakdown and confidence level
  • Regime change notifications when classification shifts
  • Circuit-breaker status and confidence alerts
  • Research improves automatically — validated model updates ship without any action from you
  • Exchange-independent research — subscribers decide independently what to do with it
Subscribe to the research — €49/mo →
Payment handled by Stripe. Stripe processes card payments — Vantegio does not receive or store your full card number or security code, but may receive limited billing and transaction information. €49/mo including applicable VAT. The final VAT-inclusive price for your billing country will be displayed before payment. Renews monthly until cancelled — cancel renewal at any time via /billing or the Stripe portal. Review the CGV and withdrawal information before subscribing.
Prefer annual? €399/year TTC — saving €189 vs twelve monthly payments. Renews annually until cancelled. Access continues until the end of your paid billing period upon cancellation. Message /annual in the bot.
From click to first research brief — about two minutes
1
Open the Telegram bot
One tap on the button above. No separate Vantegio account to create — Stripe handles the subscription.
2
Check out via Stripe
Stripe processes the payment securely. Vantegio never receives your full card number or security code.
3
First regime brief by 02:00 Europe/Paris tomorrow
You're added to the private channel. The next scheduled brief lands by 02:00 Europe/Paris, subject to service availability as described in the CGV.

Questions a skeptic should ask

Straight answers

What does the performance actually look like?

Two independent windows. First, a walk-forward OOS (2022–2024) where the model was frozen before the window opened and run forward unchanged, no refit: +76.4% CAGR, −11.2% max drawdown, Calmar 6.83 at 36% average BTC exposure. Buy-and-hold over the same period: +25.6% CAGR, −66.7% drawdown.

Second, the holdout (2025-01-01 to 2026-05-31) — data the models had genuinely never seen: annualised CAGR +30.7%, Calmar 1.87, −16.4% max drawdown. Bitcoin's annualised return was −16.3% over the same period with a −49.5% drawdown. These are annualised figures, not cumulative returns. Model Calmar 1.87 vs −0.33 for buy-and-hold. A blind holdout reduces but does not eliminate overfitting risk. Past performance does not guarantee future results.

The model targets ~36–49% BTC on average rather than 100%. Less raw exposure, but a −11.2% walk-forward worst case requires just +13% to recover — versus +200% from a −66.7% hole. Calmar — return divided by max drawdown — is one risk-adjusted measure used in this analysis. Model (OOS): 6.83 OOS vs 0.38 for buy-and-hold in this simulation.

How do I know this is real and not a curve-fit backtest?

Fair question — it's the right one to ask, because a good-looking backtest is trivial to manufacture.

The numbers on this page are walk-forward out-of-sample. The model's parameters were frozen before the test window opened, then run forward across multiple years of data — spanning bull runs, crashes, and everything in between — with no re-fitting, no cherry-picked window, no parameter nudging after the fact. It's the difference between predicting tomorrow and "predicting" yesterday.

It's not a promise about the future — nothing is. A blind holdout reduces but does not eliminate overfitting or selection bias, and results from one period do not predict another.

What happens when a new strategy fails your testing?

It doesn't ship. We've tested and rejected more strategies than we've deployed.

The ones that didn't survive a blind holdout test — where the model had genuinely never seen that data — get documented and archived. Each research question receives its own separate holdout window, opened once, and not reused. That discipline reduces, but does not eliminate, selection bias. The performance history shown on this page was produced by the model versions identified in the methodology notes, not by candidates that were tested and rejected.

Is this financial advice?

No. Vantegio publishes quantitative model outputs — regime classifications and model exposure readings — as general research. This is not personalised financial advice and nothing on this channel should be construed as a recommendation to buy, sell, or hold any asset. We are not financial advisers, we don't know your personal situation, and we never touch your funds. You are solely responsible for any investment decisions you make. If you need advice tailored to your circumstances, consult a licensed financial professional.

How often does the model output change?

About once a week on average. Historically the model changes regime classification roughly 55–115 times a year (~80 on average). Most days the output is unchanged — the research brief confirms the existing classification. Subscribers independently decide what, if anything, to do with the research. Built for people with jobs, not a screen-watching tool.

Which platforms can I use this research with?

The model output is a standardized 0–100% research variable — it is not tied to any specific platform or implementation. Subscribers who choose to use it may do so on any venue they already use — Kraken, Coinbase, Bitstamp, Binance, or elsewhere. We never custody your funds or connect to your account. Any decision a subscriber makes is their own independent decision, in full control.

How do I cancel?

Send /billing to the bot and cancel through the Stripe portal — no email, no retention call. Cancellation takes effect at the end of the period you've paid for. Full cancellation details are available on the cancellation page.

Future Bitcoin bear markets or severe drawdowns may occur. €49 a month to understand what the model is reading when they do.

Annualised CAGR +30.7% vs Bitcoin −16.3% · walk-forward MDD −11.2%, holdout MDD −16.4% · cancel renewal at any time.

Get the daily regime read →