contact us nseit

Contact Us

close contact us nseit


Pacing ahead to conquer the next-gen technology & drive business growth

Detect & prevent frauds using Graph Technology

Swati Rai | SEP 14, 2020

In any crime drama, there’s always a scene where the detective has a wall or a board full of pictures with strings all over it - connecting locations with suspects and dates. The detective often stares at the wall and tries to piece together, decode and crack the case using all his evidence. How interesting will that be if we could really implement this in our current setup and like a crime detective we could solve the cases by correlating one point with another.

Well, in today’s scenario mirroring this intense crime drama- wall- strings-decode is all possible by just sitting behind your PC screen and by just analyzing graphs. Yes you read it right; similar to that crime scene detective you can uncover frauds merely by joining dots between fraudster networks and prevent frauds. But really how is it done..??

So for that let’s figure out basics of graph database, link analysis and graph network?

Link analysis is a technique used to assess and evaluate connections between data, and therefore it is also called network visualization. Whereas, a graph network is a way of visualizing these connections between various types of information. These networks are stored in graph databases and later these graph databases help in forming links, detecting patterns, and thereby helping in graphical analytics.

{Here the circle depicts the nodes, which basically represents data points (people, businesses, accounts etc) and edge( line connecting them represents the relationship between each node and attributes and is defined by a unique identifier that details a starting or ending node, along with a set of properties}

Graphs are said to be the new frontier in Data Science

Well with all basics covered now let’s figure out how can we use the power of graph science and data in uncovering and preventing frauds in financial industry?

Did You Know - the BFSI industry at large is losing about INR 40,000 Crore every year (convert into USD) just on frauds and scams...? Fraud is big business, contributing to an estimated 20 billion USD in direct losses annually. BFSI Industry experts suspect that this figure is actually much higher, as firms cannot accurately identify and measure losses due to fraud.

What are some of the common fraudulent cases in BFSI:-

  • Credit card frauds

  • First party bank frauds

  • Insurance claims fraud

  • Refunds abuse

  • Voucher and promotions abuse

  • Online payment frauds

  • Account takeovers

No fraud prevention measures are perfect, but by looking beyond individual data points to the connections that link them your efforts significantly improve. Traditional fraud prevention measures focus on discrete data points such as specific accounts, individuals, devices or IP addresses. However, today’s sophisticated fraudsters escape detection by forming fraud rings comprised of stolen and synthetic identities or via account takeover. To uncover such fraud rings, it is essential to look beyond individual data points to the connections that link them.

Benefits of Graph Database:-

  • Intuitive and easy to use - Our brains love visualization - over 50% of the brain is involved in visual processing, so a graph network is inherently used by financial entities to understand and process data and compute risks quicker than today’s current relational databases so they can spot opportunities and threats before the competition.

  • Insightful and powerful - Since the relationships in graph database are treated with as much value as the database records themselves, the engine that navigates the connections between nodes can do so efficiently, enabling millions of connections per second. Reveal hidden connections between fraudulent customers to build a profile of what a fraudster looks like and use this information to feed into machine learning for fraud prevention

  • Save time on analysis - Graph database enables quick extraction of new insight from large and complex databases to help uncover unknown interactions and relationships. Spend less time on manual scanning and analysis to discover and identify trends, and get an always up-to-date picture of your customer behavior and fraudulent activity

To summarize, graph databases provide an excellent infrastructure to link diverse data. With an easy expression of entities and relationships between data, graph databases make it easier for the user to understand the data and find insights. This deeper level of understanding is vital for successfully detecting and preventing fraud. With a graph database, financial entities can see their data in “graphs” and more easily visualize patterns and opportunities to better predict when and where fraud might occur.

NSEIT is amongst the early adopters of the Graph Data Science and Technology solutions as we understand the BFSI industry closely and have been empowering them to be future ready. Check out our Business Transformation and understand how you can use graph data science in your setup and how you can uncover fraud and fraudulent pattern.

Swati Rai

Why do banks have a dire need of Robotic Process Automation (RPA)?

Read More

Aug 26, 2020

Transform Digital Customer On-boarding & VideoKYC Experience with AI

Read More

August 11, 2020

Rewiring Bank for the New Normal with Intelligent Automation

Read More

July 24, 2020

Contact Us

Start Growing with NSEIT Today !

Schedule a meeting with our specialist to learn how our services can
transform your business.

Contact Us