Skip to main content
ForexNews24

Pairs trading EUR/USD × GBP/USD: why it cannot be reproduced

Hypothesis instrument
EUR/USD, GBP/USD
Status
Not reproducible
Reason
required data unavailable
Portal data
EUR/USD
Author: ForexNews24 Research Desk
Hypothesis
The divergence of the spread between two historically linked pairs is temporary and reverts to the norm, allowing it to be traded market-neutrally.

Methodology

  1. The hypothesis requires synchronous quotes for two correlated instruments and an analysis of the stability of their link.
  2. The portal holds history for a single pair, EUR/USD — there is nowhere to take the second leg of the position from.

Why the hypothesis cannot be tested on our data

Pairs trading extracts profit from the relative movement of two correlated instruments. The available data is a single EUR/USD pair, so the spread of two pairs cannot be reproduced, and without it the hypothesis cannot be tested.

What a fair test would require
You would need time-synchronous series for two historically linked pairs and a cointegration test — to tell a temporary spread divergence from a breakdown of the relationship itself.

We deliberately give no figures here: a result computed on unsuitable data would be a fabrication. Blank space is more honest than a fake study.

Reproduce this

Download the exact sample and run the logic yourself — the numbers above should match.

A Binance spot EUR/USDT proxy series, not a forex-broker feed. Binance Spot REST API (api.binance.com/api/v3/klines).

Conclusion

The hypothesis cannot be tested on our data: pairs trading by definition works with the ratio of two instruments, and a spread cannot be built from a single pair.

Practical takeaway for the trader

The main risk of pairs trading is a breakdown of the link between the instruments: the divergence stops reverting to the norm, and both legs of the position move into loss at once.

FAQ

Why can it not be tested on a single pair?

Pairs trading works with the ratio of two linked instruments. A spread cannot be built from a single pair, so the hypothesis cannot be tested.

What is the main risk of the approach?

A breakdown of the link: the divergence stops reverting to the norm, and the market-neutral position turns into a directional loss on both legs.

What would be needed?

Synchronous series for two pairs and an analysis of the stability of their link (cointegration).

From research to application

In our Allocation product we implemented these algorithms with all the nuances covered across the portal.

Learn about Allocation