Market microstructure
How orders, liquidity, venue rules, participants, and execution conditions interact at a level closer to the formation of price than a simple chart pattern.
Public research map
Studying the structure beneath the price.
AUR's AI market research focuses on the mechanics that can shape price formation, the data needed to observe them, and the discipline required to avoid turning a compelling explanation into an unsupported claim.
Research areas
These are the public-safe areas AUR may name and discuss. They describe the questions and domains of inquiry, not a list of active signals or a promise that any one line of investigation will work.
Liquidity
Where available liquidity appears, disappears, or becomes expensive to access, and how a research system can distinguish observable conditions from a tidy story added afterward.
Forced flows
Market activity that may be driven by constraints, positioning, or mechanical requirements rather than a fresh discretionary view. The question is whether such pressure can be observed in time.
Cross-venue behavior
Differences and connections across venues, including how information, liquidity, and operational conditions can travel or fail to travel between them.
Data quality
Whether the data is complete, correctly timestamped, consistently defined, and available at the moment a claim says it should be available. Bad data can make a good hypothesis look better than it is.
AI research systems
How agents can generate, challenge, compare, and audit research ideas while leaving the scientific standard fixed: a fluent explanation is not evidence by itself.
Why familiar indicators are not the default answer
Moving averages, oscillators, volume-derived measures, and other standard retail indicators can be useful tools. They can help people describe markets, organize observations, or build a testable starting point. AUR does not treat them as a default source of durable advantage because their definitions are widely available, their behavior can be sensitive to regime and parameter choices, and a pattern found after repeated searching may be a selection artifact rather than a robust mechanism.
This is not a criticism of people who use those tools. It is a boundary around the question AUR is asking. If a research claim is meant to describe a durable market structure advantage, it needs a reason the information could exist before price, a clear timing path, and evidence that remains credible outside the choices that made it look attractive.
Public boundary. Active implementation details remain abstract here. AUR does not publish exact signals, thresholds, execution details, sensitive parameters, private infrastructure details, performance claims, or predictive results.