At Spotify the main search mode is search-as-you-type where new results are presented after each character entered by the user. These partial search queries are inherently very ambiguous. For instance, when typing...
Category - Nordic Data Science Summit 2016
Real-time Analytics and how to detect the abnormal – Anders Bresell
This session will be about analysing real-time connectivity data from of millions of IoT devices spread across the globe, and the supporting analytical models for a constantly changing fleet of devices and their...
Forecasting In Online Retail: Creating Value In The Full Chain – Andreas Merentitis
The talk will briefly introduce the business problems that article level forecast is addressing in retail and some of the most relevant use cases it can serve. Following that, requirements regarding such a forecast will...
Building a Data Driven Product – Åsa Bertze
Truecaller helps identify unknown incoming calls and warns users against unwanted calls through a community based spam list, contributed by more than 200 million users worldwide. In order to provide the best possible...
Machine Learning the Product – Boxun Zhang
With Spotify’s constant evolving product and fast growing user base, the user behavior in Spotify is becoming significantly diversified and complex. Thus, obtaining a holistic view of user behavior is crucial for future...
AI and GPU Databases – New Technologies To Provide You With Faster Insight – Ulrich Knechtel
Machine Learning techniques combined with processing power of Graphics Processing Units (GPU) revolutionized AI. Deep Learning evolved as most efficient technology to recognize patterns. GPU databases combine highly...
Agile Data: Enabling Data Driven Business – Jonne Heikkinen
This session gives more insight on how agile data enables the data-driven business.
Industrializing Predictive Analytics On Big Data Infrastructure – Laurent Tessier
This session gives insights of industrializing predictive analytics on Big Data Infrastructure and how to take maximum advantage of data.
Analyse Weather Data And Twitter Sentiment With Spark And Watson – Margriet Groenendijk
Weather is a source of fascination and endless conversation. When you combine weather data sets with twitter chatter about the weather, what kinds of surprising insights might you find? Are the weather sentiments on...
Feature Extraction: The Key To Accurate Models – Mikael Klingvall
This session will give you more insight on feature extraction and how it is the key to accurate models.