Predictive model performance gap between offline evaluations and online inference is a common and persistent challenge in the ML industry, often preventing models from achieving their full business potential.
Category Archives: Deep Learning
Precision in Motion: Deep learning for smarter ETA predictions
In the fast-paced world of food delivery, accurate estimated time of arrival, or ETA, predictions are not just a convenience; they’re a critical component of operational efficiency and customer satisfaction.
Beyond the Click: Elevating DoorDash’s personalized notification experience with GNN recommendation
DoorDash has redefined the way users explore local cuisine.
Improving ETAs with multi-task models, deep learning, and probabilistic forecasts
The DoorDash ETA team is committed to providing an accurate and reliable estimated time of arrival (ETA) as a cornerstone DoorDash consumer experience.
Homepage Recommendation with Exploitation and Exploration
Building quality recommendations and personalizations requires delicately balancing what is already known about users while recommending new things that they might like.
Evolving DoorDash’s Substitution Recommendations Algorithm
When expanding from made-to-order food delivery to new product verticals like groceries, convenience, and retail, new challenges arise, including how to ensure inventory will be available to fulfill orders.
Leveraging Causal Inference to Generate Accurate Forecasts
For any operations-intensive business, accurate forecasting is essential but is made more difficult by hard-to-measure factors that can disrupt the normal flow of business.
Building the Model Behind DoorDash’s Expansive Merchant Selection
An optimized merchant selection strategy has been one of the key factors that has enabled DoorDash to become an industry leader in US food delivery service.
Using Triplet Loss and Siamese Neural Networks to Train Catalog Item Embeddings
Understanding the contents of a large digital catalog is a significant challenge for online businesses, but this challenge can be addressed using self-supervised neural network models.
Reinforcement Learning for On-Demand Logistics
Overview
Introduction
What is the assignment problem at DoorDash?