Big Data Could Warn of Company Distress
The Danish Business Authority, one of Early Warning Europe’s 15 partners has developed a machine learning tool that uses publicly available accounting data to identify companies in financial distress. Of course, this is possible because for more than a decade, because the DBA, (or Erhvervsstyrelsen for our Danish audience and fans of Scandi Noir) have been using XBRL to collect financial statements from every private company in that country.
Early Warning Europe aims to improve small businesses across Europe by providing advice and support to companies in distress. In the case of potential bankruptcy, early interventions offer the best likelihood of company turnaround. With this in mind, Early Warning Europe has been developing a data-driven monitoring and early warning system to identify companies in distress at early stages of crisis.
The increasingly common requirement for reporting in Europe to be digital and standardised is creating a vast bank of data ideal for training machine learning tools. The Danish Business Authority has trained a tool on large data sets from 5 European countries to distinguish companies at early stages of crisis from financially sound companies.
This project is a great example of the wider benefits beyond investor information that digitisation and standardisation of data can have. The tool looks like a promising start to the use of machine learning and large data sets for economic modelling in this field – although Early Warning Europe caution that as reporting is still transitioning to digital in some countries data quality and therefore model accuracies vary. However, as more regulators mandate XBRL based, digital, standardised data for financial reporting, tools like this will become more effective and useful.
Read more about Early Warning Europe here and find out more about the machine learning tool in their concept paper.
