Introduction

We’re all familiar with the standard forms of graphs and charts used in almost every report or dashboard. Bar charts, line graphs, pie charts are widely used almost everywhere; there are  built-in templates within most standard reporting tools such as Excel, Tableau…

In this post we will introduce the Chord Diagram. This chart offers visualisation of datasets in a distinctive manner and provides a way to display data in a meaningful way.

The Chord Chart

The chord chart is an excellent way to visualise the inter-relationships between entities in a dataset. The connections between entities show that they share something in common. This makes Chord Diagrams useful for comparing the similarities within a dataset, or between different groups of data.

Nodes are arranged around a circle, with the relationships between points connected to each other either through the use of arcs or Bézier curves. Values are assigned to each connection, which is proportionally represented by the size of each arc. Colour can be used to group the data into different categories, which aids in making comparisons and distinguishing groups.

Our example

Suppose that you would like to compare the sector exposure on iShares ETFs. Usually sector or regional exposure in ETFs of Mutual funds factsheets are represented with bar or pie charts.

In our example it’s easy to see how iShares MSCI USA Size Factor has more weight on Industrials sector than iShares MSCI USA Minimum Volatility (yellow arc). You can also see that iShares MSCI USA Minimum Volatility has more weight on Health Care sector than iShares MSCI USA Size Factor (cyan arc).

Deeper

Below, you can see a very basic example of a chord chart. Thanks to the amazing R package circlize you can easily create your own charts. There are some additional nice examples with code here.