At Grubhub we leverage recent advances in Representation Learning to gain an automated and scalable understanding of our vast restaurant and menu catalog. We use these techniques to learn a latent food knowledge graph in order to drive better search and personalization. Particularly, we hope to share some of our advances in using: language modeling and knowledge graphs in the e-commerce setting.
Discovery and Understanding of a product catalog is an important part of any e-commerce business. Learning product interactions by building taxonomies is the traditional, however, difficult method of catalog understanding. At Grubhub we leverage recent advancements in Representation Learning, namely Sequential Modeling and Language Modeling to learn a Latent Food Graph. With our strong and scalable understanding of the product catalog, we power better search and recommendations in a much more sustainable fashion than maintaining an expensive handmade taxonomy.
By integrating pyspark and tensorflow into our end to end pipeline, we create a scalable service that spans the data collection and exploration phases and culminates in visualization tools and models served for real time use in our production environment.
We hope to highlight 3 recently successful projects:
With these 3 techniques we have a strong semantic understanding of the food graph, for example:
Topics: word2vec, object2vec, query expansion, semantic matching, personalization, search