a and real-time analytics, came defensive strategies to combat the . Thanks to the rapid advancement of financial frauds as it creates opportunities for defensive strategies, working on the principles of Big Data’ the headline screamed out to him.
Articles in the business section never caught his eyes till that day. The curiosity was back. He took the paper to the study table without even blinking his eyes. He continued reading as he sat, “Financial Fraud and Big Data!” Someone on the way to becoming a data scientist today, he had fallen in love with the term and the concept of big data around 2 years ago. Reading every article he could, about big data without fail was inculcated in his habit now.
‘Fraud detection traditionally focused on factors such as bad IP addresses or tracking unusual login patterns; Big Data is changing all of that by bringing powerful analytics solutions and tools, fast enough to detect fraud in much lesser time. Sophisticated financial crimes lead to tarnished brand images, massive institutional and investor losses and ultimately, the erosion of customers’ confidence.’
“True”, He said to himself. Without wasting time further enforcing what he had known for years, he went on…
‘Managing third party data and terabytes of historical data has been made easy by this technology, wherein banks can analyze massive data to intelligently inspect the patterns that could lead to future frauds. Through real time analytics, banks can examine transactions as they occur, thus using predictive analysis and stop the crime before it causes serious damage.
According to Experian’s 2014 fraud report, the rate of detected fraud in the financial and banking sectors has increased from 24% to 35% while third party involvement in the case of cards, loans and savings product was the highest segment among these crimes.
With Big Data, banks will monitor unusual behavior or any other malicious activity happening or most likely to occur, with precognitive capabilities. Big data use cases are endless when it comes to the banking industry. For example, if a credit card holder forgets to update his/her bank about travelling plans, then the lending institution can gain insights from mobile and social data through a fraud detection system, reducing the risk of fraudulent activities.’
Curious about the mechanics of this system, he continued...
‘Counter terrorist Unit (CTU), an anti-money laundering platform introduced by Alibaba, the world’s largest e-commerce retailer, can track and analyze accounts on the basis of its users’ behavior and later apply different levels of alerts to suspicious transactions. It redirects the user to the account only after five stages of verification that include checks on Accounts, Devices and activities followed by risk strategy and even a manual review.
Financial Institutions are using a number of Big Data and real time analytics platforms like Revolution R, Hadoop, SAS, Python, Palantir Gotham and Hortonworks among others to minimize risk and maximize transaction efficiencies within regulatory guidelines.
Big data can do even more in the banking and financial technologies domain, including inter connected customer relationships. For example, if a customer purchases a product or service from a company which is also a client of the same bank, can offer new personalized business opportunities for all the parties.’
Amazed by the ideas and software, he couldn’t resist the urge to open his laptop and read about how to install Hadoop in his own system. But only after reading the last paragraph...
‘To maintain a competitive edge, banks will have to analyze which big data trends work best for them. To proactively counter fraud and make banking experience safer for customers, it’s high time that banks start implementing these Big Data technologies and the promise they hold.’