Data

Newest Article

Data Using CockroachDB to Reduce Feature Store Costs by 75%

While building our ML feature store we learned that a mix of databases yields significant gains in efficiency and operational simplicity.

Brian Seo

Kunal Shah

12 Minute Read

Data

Balancing Velocity and Confidence in Experimentation

Figuring out how to balance our experimentation speed with the necessary controls to maintain trust is never easy. Learn DoorDash's approach.

Stas Sajin 17 Minute Read

Data

Adapted Switch-back Testing to Quantify Incrementality for App Marketplace Search Ads

Learn how DoorDash developed a switchback testing method to perform incrementality testing on an app marketplace ad platform

Kanhua Pan

Yingying Chen 11 Minute Read

Data Machine Learning

Five Common Data Quality Gotchas in Machine Learning and How to Detect Them Quickly

Data preparation, represents The vast majority of work in developing machine learning models, learn how to make things easier

Kornel Csernai

Devjit Chakravarti 10 Minute Read

Data

Building Scalable Real Time Event Processing with Kafka and Flink

Learn how DoorDash build a platform to process billions of events from different data sources, quickly, consistently and reliably

Allen Wang 19 Minute Read

Data General

Building a Source of Truth for an Inventory with Disparate Data Sources

Learn how DoorDash crowdsources data from a variety of sources to help predict realtime inventory for our new connivence and grocery product

Anubhav Kushwaha 9 Minute Read

Data

Using Back-Door Adjustment Causal Analysis to Measure Pre-Post Effects

When A/B testing is not recommended we can still quickly implement a new feature and measure its effects in a data-driven way.

Sharon Cui 9 Minute Read

Data Machine Learning

Meet Dash-AB — The Statistics Engine of Experimentation at DoorDash

Learn how DoorDash was able to test uniformly according to established best practices and reuse complex statistical methods with Dash AB

Caixia Huang

Yixin Tang 12 Minute Read

Backend Data

How We Applied Client-Side Caching to Improve Feature Store Performance by 70%

Learn about which caching libraries we considered, the analysis of our system and how we were able to use experiments to validate our approach.

Kornel Csernai 18 Minute Read

Data

3 Principles for Building an ML Platform That Will Sustain Hypergrowth

Learn about the principles and big bets that enabled to scale and maintain our ML platform which supports our data users and data scientists

Hien Luu 16 Minute Read

Data

Making Applications Compatible with Postgres Tables BigInt Update

Ensuring ID's don't get exceeded is an evolving challenge. Learn how DoorDash made our tables were compatible with our new Bigint upgrade

Maggie Fang

Amiraj Dhawan 10 Minute Read

Data Machine Learning

Introducing Fabricator: A Declarative Feature Engineering Framework

Learn how our Fabricator infrastructure integrations for ML features were automated and continuously deployed to generate 500 unique features and 100+ billion daily feature values

Kunal Shah 13 Minute Read

Data

How to Run Apache Airflow on Kubernetes at Scale

Learn how DoorDash managed to make its data orchestration more scalable and reliable with Kubernentes and Airflow

Akshat Nair 10 Minute Read

Newest Article

Balancing Velocity and Confidence in Experimentation

Adapted Switch-back Testing to Quantify Incrementality for App Marketplace Search Ads

Five Common Data Quality Gotchas in Machine Learning and How to Detect Them Quickly

Building Scalable Real Time Event Processing with Kafka and Flink￼

Building a Source of Truth for an Inventory with Disparate Data Sources

Using Back-Door Adjustment Causal Analysis to Measure Pre-Post Effects

Meet Dash-AB — The Statistics Engine of Experimentation at DoorDash

How We Applied Client-Side Caching to Improve Feature Store Performance by 70%

3 Principles for Building an ML Platform That Will Sustain Hypergrowth￼

Making Applications Compatible with Postgres Tables BigInt Update

Introducing Fabricator: A Declarative Feature Engineering Framework

How to Run Apache Airflow on Kubernetes at Scale

Building Scalable Real Time Event Processing with Kafka and Flink

3 Principles for Building an ML Platform That Will Sustain Hypergrowth