Creating trading strategies that operate on linearly correlated groups of trading instruments

We are going through the process of implementing an example of a pair trading strategy. The first step is to determine the pairs that have a high correlation. This can be based on the underlying economic relationship (for example, companies having similar business plans) or also a financial product created out of some others, such as ETF. Once we figure out which symbols are correlated, we will create the trading signals based on the value of these correlations. The correlation value can be the Pearson's coefficient, or a Z-score.

In case of a temporary divergence, the outperforming stock (the stock that moved up) would have been sold and the underperforming ...

Get Learn Algorithmic Trading now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.