Edward Thorp's Pairs-Trading Strategy

Execute Edward Thorp's Pairs-Trading Strategy on Binance perpetual futures. This statistical arbitrage approach uses 15-minute Ethereum data to profit from pric

Published · Updated · Methodology: Statistical Arbitrage

Part of: Mean Reversion

  • Methodology: Statistical Arbitrage
  • Content type: strategy
  • Timeframes: 15 minutes
  • Markets: Binance perpetual futures, Ethereum, Ethereum Classic

Indicators used

  • Returns (derived from price)

Source video

Decoded from: I Rebuilt Edward Thorp's $800M Pairs-Trading Strategy for 2025 (Full Python Walkthrough) by Algo-trading with Saleh — watch the original

Key timestamps:

  • 0:00 - Introduction to Edward Thorp and Pairs Trading
  • 1:54 - Jupyter notebook setup and Jesse framework
  • 2:44 - Exchange and date selection (Binance perpetual futures, 2025 data)
  • 3:00 - Timeframe selection (15 minutes)
  • 4:00 - Converting prices to returns for calculation (Ethereum, Ethereum Classic)
  • 4:50 - Visualizing price divergence and convergence

Strategy overview

Pairs trading takes opposite positions in two instruments that normally move together, betting that a temporary divergence between them closes. What distinguishes this entry is not the concept but the distance the concept is asked to travel: Edward Thorp ran statistical arbitrage on US equities in an era of research desks and expensive data, and the video rebuilds the same idea for 2025 on crypto perpetual futures at intraday resolution. The arithmetic of divergence and convergence is portable; almost nothing else about the setting is.

The chapter list makes that transplant explicit — Binance perpetual futures, 2025 data, a 15-minute chart, and Ethereum against Ethereum Classic as the tested pair. Pair selection is where a statistical arbitrage build is won or lost: correlation on its own is just a measurement, and a pair that holds up needs a structural reason for the two legs to stay tethered, which in this case is a shared codebase and history split by a fork. The other step the video surfaces before any signal logic — converting raw prices into returns — is the standard way to make two assets trading at very different price levels comparable in the first place.

This is a code walkthrough rather than a chart lesson: a Jupyter notebook and the Jesse backtesting framework, from the channel Algo-trading with Saleh. That format changes what the viewer is buying — a procedure you can re-run and re-parameterise, rather than a setup you eyeball. Worth reading the title carefully, too: the $800M belongs to Thorp's historical record, not to the rebuild, since a reconstruction inherits a name and a method but never the results. This entry records the concept, the source and the setting the author chose; the specific divergence thresholds, exits and sizing were not captured here, so the video itself remains the place the implementation lives.

Topics

edward thorp strategy · pairs trading strategy · statistical arbitrage · market neutral strategy · binance futures strategy · ethereum trading strategy · 15 minute strategy · crypto pairs trading · algorithmic trading · quantitative strategy · tradingview strategy · pine script

Frequently asked questions

What is a pairs-trading strategy?

Pairs trading is a market-neutral approach that goes long one instrument and short another when the historical relationship between them stretches, aiming to profit when the two converge again. Because both legs move with the broader market, the position is meant to express the spread rather than a directional view.

Why would someone trade Ethereum against Ethereum Classic?

The two chains share an origin and a codebase before a fork split them, which gives a structural reason for their prices to move together — the kind of economic link statistical arbitrage looks for, as opposed to a correlation that happens to be high in one sample. The video uses this pair as its worked example and converts both series to returns so they can be compared despite very different price levels.

Does a 1980s statistical arbitrage idea still work on crypto?

The framework ports, but nothing calibrated to it does — spread behaviour, volatility, funding costs and liquidity on a 15-minute crypto perpetual are not the equity market Thorp worked in. Any historical method needs to be re-tested on the market and period you actually intend to trade before its numbers mean anything.

How should I evaluate a strategy taken from a video like this?

Rebuild it on your own data rather than trusting a single walkthrough's results, and check that the pair relationship holds out of sample, not just in the window shown. Strategy Decoder catalogues strategies from video sources so you can see what a given creator is actually proposing before you spend time implementing it.

About this strategy page

This trading strategy was decoded by Strategy Decoder's AI from a public YouTube trading video and turned into a structured, reviewable specification. In the interactive app this page shows the full entry and exit logic, risk management settings, the indicators involved with their parameters, AlgoWizard-compatible logic and a Pine Script export ready for TradingView backtesting — plus an automated backtest verdict when one has been computed for this strategy.

Strategy Decoder catalogs 2,229 decoded strategies. Each one is extracted with confidence scoring, cross-linked to the indicators it uses, and kept up to date as new videos are processed daily. Load this page with JavaScript enabled to use the interactive tools, or start from the strategy explorer to filter by methodology, market and timeframe.

Other versions of this strategy

More decoded strategies