Eagle Eye: searching the web for early warning signals
Artificial intelligence: early warnings for credit rating migrations
Imagine if you could search the entire internet to look for early warning signals for all kinds of events; to see whether a company is likely to experience financial distress in the near future, for example. This is exactly what Eagle Eye, Deloitte’s new and state-of-the-art AI tool, does. As of 2018, the technology is live and being tested in different prototypes with clients across Europe.
Identify problems online well before they can be spotted in the financial statements
Eagle Eye was developed by the Analytics and Forensic Technology team of Deloitte, under the leadership of its Partner, Jan Balatka. It is a predictive model designed to perform online semantic analytics of the vast volume of information available on the web jointly with other metrics in order to identify potential threats and opportunities. With the use of these advanced techniques, our team was able to almost fully automate the risk calculations.
“We initially developed Eagle Eye for a financial institution that wanted to know whether their debtors were likely to go into insolvency”, explains Jan Balatka and adds: “traditional risk monitoring systems review debtors by checking their bank accounts, transaction behaviour or financial statements. But by the time you start to see warning signs there, it is typically too late – by then the company is already in financial distress.”
Before you can see it in the financial statements, early warning signals of potential decline can be observed online. This is precisely what Eagle Eye does. “It uses automated open source intelligence (AOSINT) to collect signals. It was built and tested for one particular problem, but the idea is to retrain the model for different markets and countries”, that is why we have been working on its further development jointly with the Dutch Deloitte Risk Advisory team.
Eagle Eye can process vast volumes of data and identify correlations between OSINT signals and credit risk
How does Eagle Eye know what is relevant information – a signal – and what is not? According to Jan Balatka, the solution considers any and all information it finds about the company, client or market we assign it to as a signal. With the help of machine learning, Eagle Eye then starts to analyse these signals, correlates them and recognises certain patterns. Jan Balatka adds: “Only AI can handle the vast volumes of data on the internet and find correlations between signals and credit risk that humans would not even think of. Once we find certain patterns, Eagle Eye constantly monitors the internet to look out for them”, complements Jan Balatka.
Reduced risk of default, improved credit risk management efficiency
Eagle Eye is a ready-made solution which can be customized for each client. “Depending on their needs and preferences, clients can work with an application that gives them access to the monitoring system, or we can simply supply alerts whenever a signal is spotted”, explains Roald Waaijer, Director of Risk Advisory at Deloitte Netherlands.
Jan Balatka adds: “Eagle Eye serves as a starting point. Even though the system is right in the majority of cases it flags, it must be understood that it provides an early warning, which means that the monitored company is not yet in financial distress. The client can then follow up with its usual credit reviewing process.”
What can be other areas where Eagle Eye could add value? It can be effectively utilised in areas such as compliance monitoring, fraud detection or for the identification of potential takeovers in a very early phase.
For more information on Eagle Eye, please do not hesitate to reach out to us.