Back to speakers
Talk Abstract: “How to Improve your Recommender System with Deep Learning: A Use Case”
Deep learning is without a doubt among the hottest topics in data science today. Computers are now more powerful than ever, and as a result, deep learning has been applied successfully by academics during the past few years.
However, it is still unclear how difficult it is for businesses to apply it. We want to go beyond the buzzword and share concrete examples of where deep learning has been successfully used.
Recommender systems are paramount for e-business companies. There is an increasing need to take into account all user information to provide the best, most tailored products. One important element is the content that the user actually sees: the visual of the product.
In this talk, we will describe how Dataiku improved an e-business vacation retailer recommender system using the content of images. We’ll explain how to leverage open datasets and pre-trained deep learning models to derive user preference information. This transfer learning approach enables companies to use state-of-the-art machine learning methods without having deep learning expertise.
Bio: Alexandre Hubert has been a data scientist at Dataiku for more than two years. He works on several bank use cases as loan delinquency for leasing and refactoring institutions but also marketing use cases for retailers. Before that, he worked as a trader in the city of London.
Saturday April 29th , 2017