A new profession is playing an important role in how content will be presented on Schibsted´s news sites: Data scientists. Meet the machine learning team!
At Schibsted, we use data science to build models that aggregate user behaviors and preferences. Advertisers can combine these to allocate users in groups, known as targeting segments.
In the era of BigData, where the volume of information we manage is so huge that it doesn’t fit into a relational database, many solutions have appeared. Hadoop, Spark, NoSQL are great tools for a purpose, but they don’t fit 100% of the audience.
In an earlier post we discussed a service to estimate the number of unique visitors to a website. In this article we explore the algorithms we used to build the system: HLL (HyperLogLog) and KMV (Kth Minimal Value) and evaluate each.
How we used Machine Learning to increase telemarketing conversion rates by 540%.
We built a service to estimate the number of website visitors reached by new audience segments in real time, for queries with any combination of user attributes. Here’s how we did it. By Manuel Weiss, with help from the ATE team Audience targeting and segments Schibsted’s Audience Targeting Engine (ATE)
Matching a job description with a candidate’s experience is not an easy task, even for humans.
Deep learning is changing everything – and it’s here to stay. Just as electronics and computers transformed all economic activities, artificial intelligence will reshape retailing, transport, manufacturing, medicine, telecommunications, heavy industry…even data science itself. And that list of applications is still growing, as is the list of complex tasks where
Using awareness to ensure good data quality.
What’s the most important thing for sellers on a marketplace? Setting a good price. We take a look at the dynamics of pricing and how Schibsted can help users set prices for cars.
Your age can be accurately predicted from your behavior on classified sites. Here’s how…
VG’s premium digital product, VG+ recently celebrated its fifth anniversary with over 70 000 paying subscribers. VG+ is a five year old publication published by a tabloid newspaper with no history of subscriptions. VG+ is now the fourth largest newspaper in Norway with ambitions to surpass the 100,000 subscriber milestone