Machine Learning - DoorDash Engineering Blog

Newest Article

Machine Learning Lifecycle of a Successful ML Product: Reducing Dasher Wait Times

Read how DoorDash's product development life cycle works in this new ML blog post about how we optimized when orders are sent to merchants

Rita Golovonevsky

Ram Tripathi

13 Minute Read

Machine Learning

Supercharging DoorDash’s Marketplace Decision-Making with Real-Time Knowledge

DoorDash is a dynamic logistics marketplace that serves three groups of customers: Merchant partners who prepare food or other deliverables, Dashers who carry the deliverables to their destinations, Consumers who savor a freshly prepared meal from a local restaurant or a bag of groceries from their local grocery store. For such a real-time platform as ...

Animesh Kumar

Dawn Lu

Sri Santhosh Hari 8 Minute Read

Backend Machine Learning

Next-Generation Optimization for Dasher Dispatch at DoorDash

Learn how we optimized dasher selection using data science

Holly Jin

Josh Wien

Sifeng Lin 8 Minute Read

Machine Learning

Organizing Machine Learning: Every Flavor Welcome!

Learn how we organized our ML team including its vision, values and organizational structure

Alok Gupta 7 Minute Read

Machine Learning

Personalized Cuisine Filter

The consumer shopping experience is a key focus area at DoorDash. We want to provide consumers an enjoyable shopping experience by providing the right recommendation to the right consumer at the right time for the right location. On our app, there are cuisine filters on the top of the explore page. We have built a ...

Max Li

Xiaochang Miao 7 Minute Read

Machine Learning

Analyzing Switchback Experiments by Cluster Robust Standard Error to Prevent False Positive Results

Within the dispatch team of DoorDash, we are making decisions and iterations every day ranging from business strategies, products, machine learning algorithms, to optimizations. Since all these decisions are made based on experiment results, it is critical for us to have an experiment framework with rigor and velocity. Over the last few years, we have ...

Yixin Tang

Caixia Huang 10 Minute Read

Machine Learning

Experiment Rigor for Switchback Experiment Analysis

At DoorDash, we believe in learning from our marketplace of Consumers, Dashers, and Merchants and thus rely heavily on experimentation to make the data-driven product and business decisions. Although the majority of the experiments conducted at DoorDash are A/B tests or difference-in-difference analyses, DoorDash occasionally relies on a type of experimentation internally referred to as ...

Carla Sneider

Yixin Tang 14 Minute Read

Machine Learning

Reinforcement Learning for On-Demand Logistics

Overview Introduction What is the assignment problem at DoorDash? What is reinforcement learning? Reinforcement learned assignment Moving forward Conclusion Introduction DoorDash recently held our thirteenth hackathon. Hackathons are our opportunity to explore new technologies and moon-shot ideas; they help us stay up-to-date with the world and think 10x. At DoorDash, we’re constantly thinking of ways ...

Richard Hwang

Gary Ren

Yixin Tang 11 Minute Read

Machine Learning

How Artificial Intelligence Powers Logistics at DoorDash

In May, DoorDash participated at the O’Reilly Artificial Intelligence Conference in New York where I presented on “How DoorDash leverages AI in its logistics engine.” In this post, I walk you through the core logistics problem at DoorDash and describe how we use Artificial Intelligence (AI) in our logistics engine. LAST-MILE LOGISTICS IN A THREE-SIDED ...

Raghav Ramesh 2 Minute Read

Machine Learning

Personalized Store Feed with Vector Embeddings

Customers come to DoorDash to discover and order from a vast selection of their favorite stores, so it is important to be able to surface what is most relevant to them. In a previous article, Powering Search & Recommendations at DoorDash, we discussed how we built our initial personalized search and discovery experience to surface the ...

Mitchell Koch

Aamir Manasawala 7 Minute Read

Machine Learning

Switchback Tests and Randomized Experimentation Under Network Effects at DoorDash

To A/B or not to A/B, that is the question Overview On the Dispatch team at DoorDash, we use simulation, empirical observation, and experimentation to make progress towards our goals; however, given the systemic nature of many of our products, simple A/B tests are often ineffective due to network effects. To be able to experiment ...

David Kastelman

Raghav Ramesh 13 Minute Read

Machine Learning

Powering Search & Recommendations at DoorDash

Customers across North America come to DoorDash to discover and order from a vast selection of their favorite stores. Our mission is to surface the best stores for our consumers based on their personal preferences. However, the notion of “best stores” for a consumer varies widely based on their diet, taste, budget, and other preferences. ...

Aamir Manasawala

Mitchell Koch 8 Minute Read

Machine Learning

How To Get from Salad to Sushi in 3 Moves

At DoorDash, we want to make it as easy as possible for people to discover and order from great restaurants in their neighborhoods. As part of that goal, one fascinating problem we’re tackling is how to create a personalized experience for each user on the DoorDash platform by surfacing recommendations for restaurants and other merchants ...

Mitchell Koch 3 Minute Read