Understand the odds

No. DeriveAI is research software, not a feed of picks, entries or exits. A session helps you investigate markets and contracts, Optimizer ranks contracts by their odds, and FTO is the probability behind that ranking.

Each of those is an input to your judgment. You make the decision, and DeriveAI helps you understand the odds.

It is the estimated chance the contract reaches its target before it stops out, learned from graded trade outcomes. A 60% estimate is not a promise about one trade; it is a number that should be judged across many comparable outcomes.

That is why we focus on calibration: whether predicted probabilities line up with realized outcomes over time, rather than reducing the model to a single headline accuracy number.

By inspecting the evidence rather than taking our word for it. DeriveAI is designed to publish model performance over time, including probability calibration, model versions, evaluation periods and the number of graded outcomes behind the record.

Advanced AI shouldn’t require blind trust. The goal is to make the model’s behavior understandable enough to evaluate.

We expect it to. Our own research into model decay found that a model’s edge is not a permanent property of it — performance rises, falls, recovers and drifts as market conditions change. So models are versioned, monitored after deployment, and retrained on a schedule rather than trusted indefinitely.

When model behavior changes, the evaluation record should change with it. The point is not to preserve a flattering number; it is to show how the system is behaving now.

No. You need to be comfortable reading a probability and deciding what to do with it. The workspace, Optimizer and FTO are meant to be legible to any trader who understands that markets involve risk.

The research is there if you want it, model decay, adaptive ensembles, calibration, but nothing in the product asks you to read it first.

Scorecard grades every recommendation you have been given and looks at the pattern: the probabilities you tend to accept, the expiries and strategies you favour, when your positions peak, and what waiting has cost. From that it shows you where your decisions have been strongest and weakest.

You control what any of that becomes. Nothing from your Scorecard is shared publicly unless you choose to share it.

No. DeriveAI is not a broker or an adviser, does not execute trades, and nothing it produces is a recommendation to buy or sell a security. Options trading carries substantial risk of loss and is not suitable for every investor.

Model output is an estimate of probability from historical outcomes. Past model performance does not indicate future results, and you are responsible for your own decisions.