The live streaming of child sexual abuse (CSA) is a technologically and financially enabled crime type which has proliferated in recent years. This study uses a machine learning approach to produce a proof-of-concept model for identifying the financial indicators associated with CSA live streaming.

Seven financial risk indicators were identified. Six risk indicators centred on the value of transactions, and one on the age of the individual making the transactions. The model was successful at identifying those who live streamed child sexual abuse, while making few errors in identifying those who did not.

The findings reveal an important opportunity to use financial transactions as an avenue for detecting and disrupting CSA live streaming. This proof-of-concept model offers support for an approach to targeting individuals who have previously operated with a significant degree of impunity, ultimately reducing some of the harm caused to children through live streamed CSA.