Applying Deep Learning to Ads Conversion Prediction in Last Mile Delivery Marketplace

TL;DR

This paper describes how DoorDash transitioned their Ads ranking system to deep neural networks, improving data handling, model design, and deployment, leading to significant business benefits and offering practical insights for similar ML system upgrades.

Contribution

The paper details the successful implementation of multi-task DNNs for Ads ranking in a delivery marketplace, highlighting advancements in system design and deployment strategies.

Findings

Improved Ads ranking performance with DNNs

Enhanced data and model training pipelines

Practical guidance for scaling deep learning systems

Abstract

Deep neural networks (DNNs) have revolutionized web-scale ranking systems, enabling breakthroughs in capturing complex user behaviors and driving performance gains. At DoorDash, we first harnessed this transformative power by transitioning our homepage Ads ranking system from traditional tree based models to cutting edge multi task DNNs. This evolution sparked advancements in data foundations, model design, training efficiency, evaluation rigor, and online serving, delivering substantial business impact and reshaping our approach to machine learning. In this paper, we talk about our problem driven journey, from identifying the right problems and crafting targeted solutions to overcoming the complexity of developing and scaling a deep learning recommendation system. Through our successes and learned lessons, we aim to share insights and practical guidance to teams pursuing similar advancements in machine learning systems.