Teaching a model to read the tape

Start with something familiar. The relative strength index is a simple, well-understood read of momentum: cheap to compute, easy to reason about, and an honest baseline for a lot of tape-reading work. It is also a useful on-ramp for the idea we care about, because an indicator is really just a compressed opinion about the tape. Someone decided that recent gains relative to recent losses say something worth watching, wrote that intuition down as a formula, and now a line on a chart stands in for a judgment. RSI is legible precisely because that judgment is fixed and small.

The move we are exploring is to stop hand-tuning one indicator and instead let the trader label the moments that actually mattered — the setups they leaned into, the ones they passed on, the ones they wish they had caught. Then we train a model to recognize the context around those moments rather than the outcome that followed. The features are a blend of the reads a trader already carries in their head: momentum indicators like RSI and its relatives, volatility, order-flow, time of day. The target is not a price forecast. It is the trader's attention. We are asking the model to learn what this person notices, not what the market is about to do.

Be clear about what that is and is not. It is not a crystal ball, and we would not trust one if it claimed to be. A model that learns a person's reads also inherits that person's blind spots — the setups they systematically ignore become setups the model ignores too. So it stays a signal to the human, never an autonomous decision. The human-in-the-loop principle we apply to strategies applies to the model as well. It earns trust the same way anything else in the stack does: proven out-of-sample, costed honestly against real fills and fees, and retired the moment its edge decays rather than nursed along out of attachment.

The reason to bother is narrow and practical. An experienced trader can only watch a few names closely at once; attention is the binding constraint, not insight. A model that has learned their reads can watch the whole board and raise a hand — surfacing the setups the trader would have flagged themselves if they had been looking in that direction at that moment. It does not decide. It points. That is leverage on attention, and attention is the thing that runs out first.

None of this is a model that trades for you. The goal is smaller and, we think, more durable: a model that notices like you do, so you can be in more places at once. It stays a research preview, honest about its limits, and it lives or dies by the same process discipline as everything else we run. If it stops helping the human make better calls, it comes out.