Methodology

How the models are built, and how you can check them.

A working description of the system: the parts, the rules, and what we guarantee. This is the same list we hold ourselves to when a number looks off.

01 · The ensemble

Three models, one optimizer, and no model votes.

The design rule that makes the system checkable: language models propose, deterministic math decides. The ensemble is deliberately small, and each member has one job.

A

Quant model

Produces the core numeric projections from the week's ingested data. The strongest model on the roster. Its output is a candidate, never a final answer.

B

Adversarial model

Its only job is to find the failure modes that cost money: hidden traps, committee risk, matchup cliffs. It proposes vetoes, not picks.

C

News model

Fast and cheap. It parses breaking news and market movement into bounded signals, each capped so a single story can move a projection by only a fixed amount.

D

Deterministic optimizer

Integer-linear programming over hard constraints, no language model involved. The same inputs always produce the same output. It is the only component allowed to make the final decision.

02 · Data discipline

Live data, or silence.

Every number we report is pulled during the session and carries a source and a timestamp. If a figure is not in the week's manifest or the results database, the answer is "no data." We do not fill the gap from memory.

a

Week isolation

Forward data is scoped to a single week and valid only for that week. Historical results live in a separate store, keyed by their own week. Nothing leaks across the boundary.

b

Cross-reference

No single source is trusted alone. Rankings, projections, and market signals are checked against each other; disagreements are surfaced, not averaged away.

c

Source-tagged output

Every reported figure carries its source and a fetch timestamp. A projection with no source tag is treated as garbage and discarded.

d

Stale data is flagged

If the data is older than it should be, we say so and mark the affected figures. We do not quietly proceed on stale numbers.

03 · The feedback loop

Models earn their weight.

After actuals land, we measure each model's mean absolute error and reweight the projection blend toward what has actually been right. The system gets sharper with every week, and it can tell you which source to trust.

i

Reweight by realized error

Model weights are a function of measured accuracy, not confidence. A model that has been wrong loses influence automatically.

ii

Look-ahead guard

Backtests verify that no future data leaked into the forward set. A result the guard cannot certify is not trusted, even if it looks good.

iii

Baseline first

We establish a simple baseline and measure every model against it before scaling spend. A model cannot justify its cost until it beats the cheap alternative.

iv

Money accounted

Entries, stakes, wins, and costs are kept as a real ledger. Edge is measured against money actually spent. If wins do not exceed cost, the system is told so.

A division of

The Camera Group

Aperture Analytics is the statistics and data science division of The Camera Group.

Visit the parent