Developing models for research projects is often different from production: At university you have clean data, you have clear evaluation metrics and you don't have to retrain the model on constantly incoming new data. In this talk, we will discuss what goes into putting a machine learning model like Global Orchestrator to production.
Global Orchestrator is a recommender engine developed for ING. The output of this model is used by millions of customers, and the model is based on technology employed for Netflix and YouTube recommender algorithms.
Azamat Omuraliev, Analytics Trainee @ 1-1 Analytics, UvA MSc Artificial Intelligence
Nikki van Ommeren, Data Scientist @ 1-1 Analytics, UvA MSc Software Engineering & Econometrics
The link to the lecture is still on its way!