Using Deep Learning in Production Pipelines to Predict Consumers’ Interest - Databricks

Using Deep Learning in Production Pipelines to Predict Consumers’ Interest

Download Slides

To optimize customer conversion in e-commerce and promote the right message to the right person at the right time it’s necessary to build powerful predictive models, which usually involves a lot of feature engineering to aggregate consumer related past events (clicks, page views, purchases…) and extract relevant signals. Recurrent Neural Networks (RNN) is a class of deep-learning techniques, especially good at working with sequences of inputs and at learning time-dependant patterns. They can learn from past customer behavior, and their internal state can then be used as latent features for downstream models.

In this session, we will see how to use RNN algorithms like LSTM to learn from sequences of events, and produce new features to be used in predictive models. Come see how we managed to use those RNN networks in our Spark pipelines!

Session hashtag: #SAISML2



« back
About Mathieu Despriee

Mathieu is a Machine Learning Engineer Manager at Tinyclues, focused on the productionization of Machine Learning, scalability and operability of prediction pipelines. He has been using Apache Spark since 2014, and has extensive experience with Hadoop and other distributed frameworks in production. He graduated with a Masters in CS from a French engineering school. After he gained experience in several startups and through technology consulting.