Estimating unknown links: Network reconstruction

Kimmo Soramäki and Samantha Cook

Chapter 2 presented several methods for constructing networks from real data, including adjacency matrices, transaction data (eg, payments or other financial transactions) and similarity measures (eg, correlation networks). It may also be the case that networks of interest do not have complete linkage data readily available. In an exposure network, for example, nodes are financial institutions and links represent bilateral exposures between institutions. It is common, however, that bilateral exposures are unobserved or unavailable, and only the marginal values, ie, the total assets (sum of outgoing link weights, or out-strength) and liabilities (sum of incoming link weights, or in-strength) of each institution, are available for constructing networks. How to reasonably “fill in the blanks” – ie, to estimate the underlying exposure network from the partial information available – has been an active area of research in recent years. This chapter provides an overview of many of the methods that have been developed for network reconstruction, as well as a discussion of how to choose from the different methods available. Squartini et al (2018) is an excellent resource for more details

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to View our subscription options

You need to sign in to use this feature. If you don’t have a account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here