LinkedIn Backs Machine Learning By Open-Sourcing Internal Toolkit Named FeatureFu

Professional networking firm LinkedIn today announced a new open-source toolkit named FeatureFu which helps developers to build their machine learning models around statistical modelling and decision engines. The feature uses a small Java directory called Expr that developers can use to edit and build over an existing set of features. The company is aiming to unify the feature engineering process, thereby removing one of the major drawbacks many large-scale recommendation systems face. The problem, according to LinkedIn, is that most of today’s systems constitute of two major teams: one that handles the offline modeling and one that takes care of the online feature-serving/model-scoring part of the system. The division in the system leads to many problems that LinkedIn believes can be solved by FeatureFu. […] This system is brittle and vulnerable to online/offline parity issues because features…


Link to Full Article: LinkedIn Backs Machine Learning By Open-Sourcing Internal Toolkit Named FeatureFu