Emil Eifrem, CEO of Neo Technology, explores the hidden connections between two very different industries
At first glance, the idea that the banking or finance sector could learn a trick or two from the online dating industry is laughable. After all, while the former is heavily regulated, deeply complex and integral to our economy; the latter is frivolous by comparison.
Dating, as is often said, is a numbers game! And organisations such as Match.com, eHarmony and Zoosk rely on very sophisticated technology as they sift through vast customer bases to create the most compatible couples. Specially, they rely on data to build the most nuanced portraits of their members that they can, so they can find the best matches. This is a business-critical activity for dating sites – the more successful the matching, the better revenues will be.
One of the ways they do this is through graph databases. These differ from relational databases – as conventional business databases are called – as they specialize in identifying the relationships between multiple data points. This means they can query and display connections between people, preferences and interests very quickly.
WANT TO BUILD A FINANCIAL EMPIRE?
Subscribe to the Global Banking & Finance Review Newsletter for FREE Get Access to Exclusive Reports to Save Time & Money
By using this form you agree with the storage and handling of your data by this website. We Will Not Spam, Rent, or Sell Your Information.
Applying Dating Insights to the Financial Sector
So where do financial institutions come in? Dating sites have put graph databases to such effective use because they are very good at modelling social relationships, and it turns out that understanding people’s relationships is a far better indicator of a match than a purely statistical analysis of their tastes and interests. The same is also true of financial fraud.
The finance and banking sector lose billions of pounds each year as a result of fraud. While security measures such as the Address Verification Service and online tools such as Verified by Visa do help prevent some losses, fraudsters are becoming increasingly sophisticated in their approach. Over the last few years ‘First-Party’ fraud has become a serious threat to banking – and it is very difficult to detect using standard methods. The fraudsters behave very similarly to legitimate customers, right up until the moment they clear their accounts and disappear.
One of the features of first-party fraud is the exponential relationship between the number of individuals involved and the overall currency value being stolen. For example, ten fraudsters can create 100 false identities sharing ten elements between them (name, date of birth, phone number, address etc.). It is easy for a small group of fraudsters to use these elements to invent identities which to banks look utterly genuine. If each fraudster took out three accounts, credit cards or loans, worth £5,000 each, the potential loss is £1.5 million.
The ability to maximize the ‘take’ by involving more people makes first party fraud particularly attractive to organised crime. The involvement of networks of individuals actually makes the job of investigation easier, however.
The ‘Social Network’ Analysis
Graph databases allow financial institutions to identify these fraud rings through connected ‘social network’ analysis. This involves exploring and identifying any connections between customers before looking at their spending patterns. These operations are very difficult for conventional bank databases to explore as the relational database technology they are built in is designed to identify values, rather than explore relationships within the data.
Importantly, taking new insights from the connections between data does not necessarily require gathering new data. Instead, by reframing the issue within a graph database financial institutions are able to flag advanced fraud scenarios as they are happening, rather than after the fact.
It therefore follows that the very same ‘social graphs’ that dating sites use to find matches between people, also represent a significant advance in the fight back against fraud, where traditional methods fall short. In the same way that graph databases outperform their relational counterparts in mapping out social networks, they can also be put to work in other contexts, too – as recommendation engines, supporting complex logistics or business processes, or as customer relationship management tools.
From fraud rings and educated criminals operating on their own to lonely-hearts searching for love – graph databases provide a unique ability to discover new patterns within hugely complex volumes of data, in real time. Ultimately, in either case it can save the businesses time and money and offer a competitive advantage – something that any bank is sure to love.