For every growing company using an out-of-the-box search solution there comes a point when the corpus and query volume get so big that developing a system to understand user search intent is needed to consistently show relevant results. We ran into a similar problem at DoorDash where, after we set up a basic “out-of-the-box” search ...
DoorDash operates a large, active on-demand logistics system facilitating food deliveries in over 4,000 cities. When customers place an order through DoorDash, they can expect it to be delivered within an hour. Our platform determines the Dasher, our term for a delivery driver, most suited to the task and offers the assignment. Complex real-time logistic ...
When a company with millions of consumers such as DoorDash builds machine learning (ML) models, the amount of feature data can grow to billions of records with millions actively retrieved during model inference under low latency constraints. These challenges warrant a deeper look into selection and design of a feature store — the system responsible ...
Learn how we analyzed over 100K online delivery menus to develop menu best practices
Learn how our team optimized prep time estimates while overcoming censored data
To speed up the development of new features we needed a way to increase our experiment capacity. Learn how we improved it by 4X
Learn the challenges and best practices to successfully growing a data platform organization
Using Heterogeneous Treatment Effects to improve personalization
When the COVID-19 pandemic significantly changed how people took their meal, DoorDash had to retrain demand prediction machine learning models.
DoorDash engineers built Curie, a new experimentation analysis platform, to better gauge the success of product experiments.
Learn how we built a classification model quickly, cheaply, and at scale
Learn how we utilized cost curves to automate our marketing campaigns at scale
Susbscribe to the DoorDash engineering blog