BT

Disseminando conhecimento e inovação em desenvolvimento de software corporativo.

Contribuir

Tópicos

Escolha a região

Início Apresentações Improving a recommendation engine with transfer learning

Improving a recommendation engine with transfer learning

Favoritos
28:51

Resumo

In this talk, we will describe how we improved an online vacation retailer recommender system by using the information in images. We’ll explain how to leverage open data and pre-trained deep learning models to derive information on user taste. We will use a transfer learning approach that enables companies to use state of the art machine learning methods without needing deep learning expertise.

Minibiografia

Pierre Gutierrez is a lead data scientist at Dataiku Labs in Paris, France. In the past few years, he has been working on state of the art Data Science and Machine learning problems in a large variety of sectors such as e-business, retail, insurance, or telcos. He has experience in topics such as fraud detection, bot detection, recommender systems, or churn prediction.

Sobre o Evento

Nos dias 21 e 22 de Junho de 2017, São Paulo recebeu a primeira edição do PAPIs.io Connect no Brasil. Com o intuito de apresentar casos reais de utilização de Machine Learning, o PAPIs contou com mais de 20 palestras apresentando cases e ferramentas de empresas nacionais e internacionais.

Gravado em:

26 set 2017

BT