Improving ETA Predictions with Advanced Deep Learning Architecture [DoorDash]
An episode of the Snacks Weekly on Data Science podcast, hosted by Pan Wu, titled "Improving ETA Predictions with Advanced Deep Learning Architecture [DoorDash]" was published on July 22, 2024 and runs 14 minutes.
July 22, 2024 ·14m · Snacks Weekly on Data Science
Summary
In this episode, we will discuss the importance of Estimated Time of Arrival (ETA) for DoorDash and how the company enhanced its machine learning model through three key directions: upgrading from a tree-based model to a deep-learning architecture, adopting a multi-task modeling approach, and leveraging probabilistic models. For more details, you can refer to their published tech blog, linked here for your reference: https://doordash.engineering/2024/03/12/improving-etas-with-multi-task-models-deep-learning-and-probabilistic-forecasts/
Episode Description
In this episode, we will discuss the importance of Estimated Time of Arrival (ETA) for DoorDash and how the company enhanced its machine learning model through three key directions: upgrading from a tree-based model to a deep-learning architecture, adopting a multi-task modeling approach, and leveraging probabilistic models.
For more details, you can refer to their published tech blog, linked here for your reference: https://doordash.engineering/2024/03/12/improving-etas-with-multi-task-models-deep-learning-and-probabilistic-forecasts/
Similar Episodes
Jun 19, 2025 ·46m
Jun 13, 2025 ·40m
May 20, 2025 ·80m
May 13, 2025 ·74m
May 7, 2025 ·64m