Skip to content
Oxarus
LOOP

each
area
feeds
the
others.

The four areas may look like separate products, but they run on shared infrastructure. What research measures becomes a robot rule; a control built in engineering carries over unchanged to the terminal and the robots.

ResearchRobots

A finding becomes a rule

If a level's name doesn't change the odds of a break, no robot gets a rule that says 'open a trade at this level.' Only behavior that holds up against a control group makes it into a rule.

HANDOFFlevel_study.ipynb → rules.mdPROOFLevel families ~41%, control ~40%: no difference.

Pick a handoff, or click an area in the diagram.

STANCE

we
have
skin
in
the
game.

We run the systems we build on our own capital first. Before we use an idea, we measure it and compare the result with a control group under the same conditions. We don't publish result figures; this page describes the method.

GATES AN IDEA HAS TO CLEAR
  1. 01CONTROL

    No control group, no finding

    Every measurement is compared against matched samples drawn at random under the same conditions. No difference means no finding.

  2. 02REPLICATION

    An idea that fails on two pairs is shelved

    A result on a single pair can be chance. It has to replicate on at least two independent pairs, across different years.

  3. 03INVENTORY

    Tail-event days get their own inventory

    Sudden gaps, liquidity pullbacks and surprise decisions are logged separately, so they don't disappear into the average.

  4. 04HALT

    The stop rule is written before the start rule

    Before a system goes live, the conditions under which it stops are defined in code and in documentation.

QUANT

let's
talk
markets.

Terminal, custom robot, research or infrastructure: tell us what you're working on, and we'll route you to the right team.

info@oxarus.com