Facebook to fight financial scam with new machine learning techniques

Share the joy
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  

Credit: https://www.youtube.com/watch?v=Jf5LUmXu8Tk

Being a victim of financial scam can be very frustrating to put it mildly. It throws you off balance, and beside the fact that it affects you financially, it also deals a psychological blow on you. It is an everyday thing—people fall for various financial-related scams virtually everyday online. Can it be totally eradicated? Maybe not, but Facebook thinks it can actually fight this menace with its new machine learning techniques.

Facebook’s new machine learning techniques, according to the company, have helped the company to detect more than half a million accounts that are fraud-related.

The social media in recent years has been prone to financial scam—leaving millions of people vulnerable. Financial scams on Facebook and other places online take different forms, including romantic messages from attractive strangers, promises of lottery winnings, or appeals to help someone in need, explains the social networking behemoth. All these are aimed at tricking you so you can part with your money.

“Our new machine learning models are trained on previously confirmed scams to help detect new ones. For example, we look for instances where people are reaching out to others far beyond their typical network of connections, or in unusually large volumes, along with other behavior patterns,” Scott Dickens, Product Manager wrote.

Facebooks says it is already taking a number of measures to deal with scam on its platforms, and the newly introduced techniques are just part of it. The company said it has a dedicated set of trained reviewers that are tasked with the responsibilities of taking down scams. It also adds that feedbacks from users have been of great help. Based on examples of scam-related activities it collected in the last couple of months, the company said actions have been taken against more than half a million accounts that were involved in promoting or encouraging scams on its platform.

Credit: https://www.facebook.com/notes/facebook-security/introducing-new-machine-learning-techniques-to-help-stop-scams/10155213964780766/

Suspected scammers are made to “complete a few actions to demonstrate that they are not operating a fake account or misrepresenting themselves.” One is deemed a suspect once the Facebook machine learning technique assess that an account is likely associated with scam behavior.

Until they do this, the account can’t be used to reach others. If the owner fails the verification, or if our Community Operations team determines that there is a violation of our policies, the account will be removed.”

While this is a great move towards dealing with financial scam on Facebook, users should themselves be reminded that they have a big role to play to help address the problem.

Extra caution should be taken not to divulge too much information on not just Facebook, but on any platform. You should also show extra caution when relating with people you don’t know on Facebook.


Share the joy
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  

Author: Ola Ric

Ola Ric is a professional tech writer. He has written and provided tons of published articles for professionals and private individuals. He is also a social commentator and analyst, with relevant experience in the use of social media services.

Share This Post On