AI Case Study

Bytedance ranks web content according to the preference of each user by analysing their behaviour using machine learning

Bytedance offers Toutiao - an app which uses machine learning to discover content from the web for easy consumption. The algorithm presents content ranked according to the preference of each user uncovered by analysing clicks, views, comments etc on the app. The app is extremely popular in China with more than 120m users who spent ~76 minutes on the app daily.

Industry

Consumer Goods And Services

Media And Publishing

Project Overview

Bytedance's AI sources news, social media content, videos, images etc all over the world wide web and deliver this in various forms to users. Toutiao utilizes AI technologies and strategies like data mining and user behavior analysis to connect its customers with customized advertising campaigns.

Reported Results

The app is extremely popular China with 120 Million users who spent 74 minutes per day on the app

Technology

" Toutiao utilizes AI technologies and strategies like data mining and user behavior analysis to connect its customers with customized advertising campaigns."

Function

Marketing

Product Marketing

Background

"Founded in 2012, Bytedance is a technology company that specializes in the use of artificial intelligence to link people with large amounts of information. The company's flagship app, Toutiao, offers a personalized ranking of news, videos, and content from thousands of media outlets and millions of users and updates them in real time based on a user’s actions."

Benefits

Data

"In 2017, Toutiao grew from a reported 70 million daily users to 120 million, who spend an average of 74 minutes a day in the app."

From the Economist,
"Toutiao sources its content from 4,000 partner sites, from China’s state-owned media titans to its buzziest blogs. Users’ newsfeeds are constantly updated based on what its machines have learnt about reading preferences, from things like taps, time spent on an article and location.
Toutiao claims to have a user figured out within 24 hours."