The same pipeline that prices sports and equities, retrained on assets that never close. Each session the engine scores the liquid crypto universe across seven weighted factors, calibrates a probability, compares it against what perps and options already price, and publishes only the rotations that clear the edge threshold.
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.
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.
Depth and expected slippage at the intended clip size remove anything unfillable at the quoted price.
Momentum, funding stress, breadth, depth, on-chain flow, vol term structure and risk beta collapse into one composite.
The composite maps to a probability using out-of-sample periods only, so the quoted number is the number that historically resolved.
That probability is compared against perp and options pricing. No material gap, no publication.
Survivors get a fractional-Kelly weight with a hard cap plus an explicit invalidation level.
Every run writes its state, item count and duration, so a missed cycle is visible publicly.
What members ask before unlocking AI Crypto Momentum Desk.
Directional momentum calls across majors, funding and basis dislocations, and realised-versus-implied volatility reads — each with a calibrated probability, expected move and fractional-Kelly weight.
Majors and high-liquidity alts only. Order-book depth and expected slippage at the intended clip size are a weighted factor, so thin assets are screened out rather than ranked.
Digital assets never close, so the engine scores every session and writes a heartbeat each run. Its live state is published on the engine status board.
The model card publishes the settled hit rate and Brier score behind the version currently running, with the sample it was measured on. Crypto momentum edges are thin and regime-dependent.
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.