Using ML for personalizing food recommendations

This will be presented in English.

Maulik Soneji (Gojek), Jewel James (Gojek)
16:2017:00 Thursday, June 20, 2019

必要预备知识 (Prerequisite Knowledge)

  • General knowledge of Elasticsearch (useful but not required)

您将学到什么 (What you'll learn)

  • Learn how to apply ML for search relevancy systems and how to make trade-offs between search relevance and response times in high throughput systems
  • Understand how to use ML models along with Elasticsearch for reranking documents

描述 (Description)

GoFood, GO-JEK’s food delivery product, is one of the largest of its kind in the world. It uses ML to personalize restaurant results based on the user’s food and taste preferences.

Maulik Soneji and Jewel James outline the approaches they considered and the lessons they learned during the design and successful experimentation of GoFood. You’ll learn the trade-offs they had to make between accuracy in relevance estimation and response time while designing search relevancy systems. They formulated the estimation of the relevance as a learning-to-rank ML problem, which made the task of performing the ML inference for a very large number of customer-merchant pairs the next hurdle. The bottleneck here is that if the ML inferencing happens after all candidate restaurants in the user’s location are retrieved from the database, the time taken for information retrieval and inferencing leads to slower response times. Ultimately, this called for a design that performs the inferencing before the information retrieval step.

Discover how they scaled the experiment while still maintaining their service-level agreements (SLAs). It could help you decide how to build and implement data pipelines and the software architecture when using ML for relevance ranking in high-throughput search systems.

Photo of Maulik Soneji

Maulik Soneji


Maulik Soneji is a product engineer at Gojek, where he works with different parts of data pipelines for a hypergrowth startup. Outside of learning about mature data systems, he’s interested in Elasticsearch, Go, and Kubernetes.

Photo of Jewel James

Jewel James


Jewel James is a data scientist at Gojek.

Comments on this page are now closed.


011071b6 3e8a9859 | DATA SCIENTIST
2019-03-03 08:04 CST

Would non-chinese audience be able to understand the talk?