DeriveAI is a ROUTUR, Inc. company.
The models are built and evaluated by DeriveDX Quantitative Labs, ROUTUR's research arm.
DeriveAI is research software for individual traders. It helps you research opportunities, understand the probability associated with them, and learn from your own decisions over time. DeriveAI is not a broker or a dealer, is not an investment adviser, does not hold client funds, and does not place, route or execute trades. Nothing in the product acts on your behalf.
Nothing on this website or in the product is investment advice, a recommendation to buy or sell any security, an offer or solicitation to trade, or a statement that any transaction is suitable for you. DeriveAI does not know your circumstances, objectives, tax position or risk tolerance, and its output is not personalised to them. Every decision you take is your own, and you should consider taking independent professional advice before acting.
Trading involves risk, and you can lose money. Options trading in particular involves substantial risk of loss and is not suitable for every investor: options can expire worthless, losses can exceed expectations, and certain strategies carry the risk of loss greater than the amount initially committed. Markets are uncertain. DeriveAI is built to help you reason about that uncertainty; it cannot remove it, and it does not try to.
FTO returns probability estimates informed by a history of graded trade outcomes. A probability is an estimate of odds, not a guarantee — an outcome going the other way on any single occasion does not by itself invalidate the estimate. Models are identified by version, evaluated over stated periods and market conditions, and their performance is expected to change over time as those conditions change. Past model performance does not indicate future results.
We monitor models after deployment rather than assuming a model that performed well continues to. When performance drifts, that appears in the published record.
Some numbers shown on this website and in product screenshots are examples used to demonstrate an interface, not records of real results. Where a figure is illustrative it is labelled as such. Illustrative figures are not performance claims and should not be read as any indication of what DeriveAI’s models have achieved or will achieve.
You are responsible for your account and for keeping your credentials secure. Accounts are for one person and are not to be shared. You may use DeriveAI’s output for your own decisions, but not to scrape, resell, redistribute or republish model output, nor to present it as your own or as anyone else’s advice.
To build your Scorecard, DeriveAI analyses how you use the product: the opportunities you evaluate, the probabilities you tend to accept, the characteristics of the contracts you look at, and the patterns in those choices over time. That analysis exists to tell you something useful about your own decisions.
Your Scorecard is private by default. Nothing from it is published unless you choose to share it, sharing is opt-in, and you control which parts. You can export your Scorecard data, and cancelling a paid plan does not delete it.
Both these terms and the models behind the product will change. Where a change materially affects what you get or how your data is used, we will say so rather than quietly updating this page. The effective date will be stated here once this draft has been reviewed and published.
Questions about this page, about what a model output means, or about your data can go to hello@deriveai.example. Questions about methodology and calibration are welcome too — they usually reach the people who built the models.