Carnegie Mellon University

Christos Faloutsos on using Machine Learning to fight social media fraud

March 27, 2018

Fighting Fraud in Social Media with Data Science

How many friends do you have on social media? How many of your friends are also friends with each other? These two simple questions may hold the answer to how normal you are, at least from a data science point-of-view. It’s information like this that Christos Faloutsos and his team at Carnegie Mellon University use to find fraudulent profiles in social networks and elsewhere on the web.

How to find out what’s normal

But how do you find out what’s popular? Which indicators should you look at to analyze a user’s behavior? Christos laughs when I ask the question. “Well, it’s kind of an art. You have to figure out how to extract useful features from a graph,” he says. The process of choosing features to analyze is a manual labor, even in times of AI. Experience, trial-and-error, as well as large amounts of validation data, are key in this phase of a project.

Fraudsters work in lock-step

Fraudsters work in synchronized behavior. Christos gives the example of two competing sellers on the Indian online retailer Flipkart, with whom he wrote a paper on the topic. “You want to sell shoes on Flipkart. I’m your competitor, so how do I boost my sales? [I get] 4,000 people to rate you with one star [out of five] and ruin your reputation.” These people can be easily hired, he explains. They may be real people, but the way they do work gives them away. “Usually, they will [post their review] more or less on the same day, because the customer wants results quickly.”

Read the full article on Medium:

Article courtesy of Sven Chmielewski on Medium

Machine Learning Department -