SMS vendors see a lot more SMS traffic around the world across different industries, hence they are also a potential solution provider to SMS pumping fraud by leveraging Machine Learning capabilities with their own network of data. The larger the traffic, the better the detection.
For example, in a solution called Twilio Verify, when Twilio sees a pattern of attack happening at Uber, the same kind of traffic will also get identified and flagged for other the customers to attain network effect.
Yeah, that's true. But, for a large scale system, it cannot only rely on one provider. Sticking the solution with only one SMS provider might make the business hard to scale. Therefore, creating their own detection logic is necessary.
Absolutely key to have a fraud detection logic. The hardest part to build it in-house is that the fraudsters would keep changing their parameters to crack the wall. If a company sees enough traffic (vol. variety, countries etc.) to make a dynamic detection system, they totally should do it in-house to reduce dependency.
Wondering content, Roy.
SMS vendors see a lot more SMS traffic around the world across different industries, hence they are also a potential solution provider to SMS pumping fraud by leveraging Machine Learning capabilities with their own network of data. The larger the traffic, the better the detection.
For example, in a solution called Twilio Verify, when Twilio sees a pattern of attack happening at Uber, the same kind of traffic will also get identified and flagged for other the customers to attain network effect.
Jason,
Yeah, that's true. But, for a large scale system, it cannot only rely on one provider. Sticking the solution with only one SMS provider might make the business hard to scale. Therefore, creating their own detection logic is necessary.
Absolutely key to have a fraud detection logic. The hardest part to build it in-house is that the fraudsters would keep changing their parameters to crack the wall. If a company sees enough traffic (vol. variety, countries etc.) to make a dynamic detection system, they totally should do it in-house to reduce dependency.