Code.Talks 2019: Using the Amazing World of Embeddings for Recommendations

Machine Learning, Neural Networks, Word2Vec, Doc2Vec… You know some of these words? Congratulations! You don’t? Neither did I when we started experimenting with such technologies at Joblift. This was the first step of our journey towards creating a career advisor that offers personalized jobs based on how you act on our website.

This talk will show how you can benefit from Machine Learning and that you’re able to facilitate those benefits even with basic background knowledge. We will provide an overview on word embeddings as well as which problems we faced and with what points we still struggle.

To do so we’d like to guide you through the steps we took for getting closer to our vision; Starting with simple boosting on jobs having similar attributes like title and company, then using Doc2Vec for calculating similarity based on job descriptions and transferring that technique to learn embeddings from click histories to recommend jobs based on user behaviour.

Code Talks 2019: Using the Amazing World of Embeddings for Recommendations

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: