ASCEND
ASCEND-RISK 2.0 · daily cadence · 7 weighted factors

AI Bankroll Manager

Edge without staking discipline is noise. This engine sizes every Ascend play against your actual roll using fractional Kelly, de-rates for correlation and calibration drift, models the drawdown distribution, and tells you to shrink before variance does it for you.

Verifying your access…

What lands, and when

The schedule this engine runs on. Every run writes a heartbeat, so if a cycle is late you can see it on the status board rather than guessing.

DailyToday's card sized against the current roll and drawdown state.
DailyCorrelation caps recomputed across the live board.
WeeklyVariance report against expectation for the trailing week.

The factor stack

7 weighted inputs, published in full. Weights sum to 1.0 and are refit against out-of-sample periods — never against the window being reported.

22%Realised EdgeSettled edge of the tier over its trailing 250 plays.
18%Calibration DriftGap between stated and settled probability by bucket.
16%Ticket CorrelationShared game, player and market exposure across the card.
15%Payout VarianceDispersion of returns at the prices actually available.
13%Closing-Line ValueAverage beat versus the closing number.
9%Limit AvailabilityStake that clears at the quoted price without moving it.
7%Drawdown StateCurrent position inside the modelled drawdown envelope.
Model card
Trailing 250 settled plays per tier
Model version
ASCEND-RISK 2.0
Weighted factors
7
Calibrated band
40% – 80%
Kelly fraction
0.25x
Hit rate
57.8%
Brier score
0.2380
  • Realised Edge · 22% weight — Settled edge of the tier over its trailing 250 plays.
  • Calibration Drift · 18% weight — Gap between stated and settled probability by bucket.
  • Ticket Correlation · 16% weight — Shared game, player and market exposure across the card.

How a cycle is built

1 · Settled edge read

The realised edge of each tier over its trailing 250 plays becomes the base input — stated confidence is not.

2 · Calibration check

The gap between stated and settled probability by bucket de-rates any tier that has been over-claiming.

3 · Correlation map

Shared game, player and market exposure is collapsed so six plays on one game are not sized as six plays.

4 · Variance model

Return dispersion at the prices actually available, plus the stake that clears without moving the number.

5 · Drawdown state

The account is placed inside its modelled drawdown envelope, and exposure falls as it deepens.

6 · Sized card

Fractional Kelly with a hard cap produces the day's stakes, published with the reasoning behind each one.

Frequently asked questions

What members ask before unlocking AI Bankroll Manager.

What does the bankroll engine actually output?

A sized card: a stake per play as a fraction of your roll, correlation caps across same-game exposure, and where the account currently sits inside its modelled drawdown envelope.

Why is my stake smaller than a Kelly calculator says?

The engine uses fractional Kelly with a hard cap, and it de-rates for ticket correlation and calibration drift. Full Kelly is optimal only if your probabilities are exactly right — they never are.

Does it use my real results?

It sizes from settled results: the realised edge of each tier over its trailing plays and the measured gap between stated and settled probability, so a tier that over-claims shrinks automatically.

Will it stop me losing money?

No. It keeps losing stretches survivable by bounding exposure. A thin genuine edge still produces losing weeks, and no staking rule changes that.

The rest of the fleet

Risk disclosure

Ascend publishes quantitative research, not investment or betting advice. Every published call can lose, past model performance does not predict future results, and sizing is your decision. Never risk capital you cannot afford to lose.