How Snapchat is using Machine Learning ?

The very famous social media app Snapchat is all around the corner or let's in pocket of teens and even adults.

While the addiction is concerning or not is still debatable, something surely concerning is what's circulating around the app.

Creating Filters :

For filters, Snapchat uses AI-powered lenses with small machine learning models to detect a face, differentiate the structures and features within it, and then create a 3D model face.

This process is completed using "Image Processing", "Facial Landmarks" - plotting points on face and comparing it with collected data sets and active "Shape Modelling" which creates a virtual face and aligns it with the actual face.

Targeting Ads :

They call it as goal-based bidding which is an iterative improvement to advertising optimization on Snapchat.

The targeting technique allows advertisers to tell Snapchat whether they value ad engagement - such as swiping through to install an app, visit a website or watch a movie trailer - versus simply reaching the maximum number of users.

Avoiding Drug Deals :

Last October NBC News did a story about the troubling drug deals presumably taking place on the app. Which left everyone shocked.

In the report, it spoke about teens and young adults who had bought what they believed to be a prescription pill, but turned out to be a counterfeit pill containing deadly doses of fentanyl.

Since that report Snapchat has been ramping up its efforts to thwart drug deals on its platform.

Jan 18, Snap stated that it has a zero tolerance for drug dealing on Snapchat.

It states to deploy tools that proactively detect drug related content with the help of data, AI and ML in the matter, helping the law enforcement to support their investigations.

It will also provide in-app information and support to Snapchatters who search for drug-related terms through a new educational portal, Heads Up.

Snapchat's use of AI and ML proactively detects 88% of drug related content.

Snapchat Machine Learning :

Training Data -> Training Process -> .ONNX/.PB -> ML Components

Snap ML allows you to make your lenses even more intelligent with Machine Learning.

Just plug in an ML model to apply art style to the camera feed, use custom segmentation masks, attach images to custom detected objects, detected objects, understand what is in the scene and more.