Meet the team responsible for Paytm’s securityBengaluru, India | Red Newswire | Dec 31, 11:00 AM IST
Paytm’s headquarters might be in Noida, but its lifeline operates far away. It’s not the Paytm’s investor Alibaba we are talking about, but a Toronto-based team that safeguards all its transactions.
There is no doubt about Alibaba’s support to the company, the app now has 125 million users.
This team based in Toronto is a vital part of Paytm’s success as it manages critical issues such as customized advertising, user interface and of course fraud detection! The team is a bunch of data scientists who ensure each transaction made through Paytm is safe and secure.
Apart from its culture, scenic beauty, music and media, Toronto is also known for its data scientists. Vijay Shekhar Sharma, founder of Paytm tapped this talent a year ago. This decision of his was aided by one of his senior employees Harinder Takhar who relocated there. Takhar hired 30 data scientists from Asia, Europe and US.
Takhar now heads this team and take care of the transactions and revenue opportunities.
Paytm has one team appointed exclusively for fraud detection and two others for advertising analytics.
Sharma says, "You can't become a playground for fraudsters,” since a huge number of transactions happen over the site every day and there are a lot of tricksters at work.
The fraudulent level on Paytm is 0.5% of the total transactions and it aims at lowering it to 0.1%. Sharma added, “fraud can't be completely eliminated. But when you are working on low margins, like we have at 2.5%, we have to constantly check and control fraud."
Chief technology officer at Paytm, Adam Muise says, “There are more than a million transactions happening every day on Paytm, generating multiples of 100s of terabytes of data. Our challenge is to detect frauds and keep ahead of the fraudsters." And to accomplish this Paytm requires deep computing skills. One of the data scientists at Paytm says, “And it's a dynamic problem — fraud today is totally different from fraud tomorrow. My focus at Paytm is fraud detection and risk mitigation. For instance, fraud, points out Armando need not always be misusing a credit card, but misusing an offer. The fraudster comes with an intention to compromise the system." The scientists make sure that the system is not being compromised by same user and that it is actually users buying products and not shopkeepers trying to buy things at discount only to sell them at a higher price later on. Armando is a nuclear scientist and had previously worked at CERN.
Another data engineer Honsa Kozel works on improving ads target. Kozel is masters in geophysics. If you are looking to buy a laptop, engineers ensure that the ads related to laptop cases and travel bags are pushed to you. Kozel says, “We analyse signals — if people are looking for sports goods, we increase supply of such products on the app."
One thing about digital transactions is that very little trail is left behind. Sharma says that he has the right team to track those trails and it will be 200 large by next year. He says since next year will see the beginning of mobile commerce and “Mobile will be the primary way of shopping, we can't afford fraudsters to spoil the party."
Source: ET Bureau