Book Image

Driving Data Quality with Data Contracts

By : Andrew Jones
Book Image

Driving Data Quality with Data Contracts

By: Andrew Jones

Overview of this book

Despite the passage of time and the evolution of technology and architecture, the challenges we face in building data platforms persist. Our data often remains unreliable, lacks trust, and fails to deliver the promised value. With Driving Data Quality with Data Contracts, you’ll discover the potential of data contracts to transform how you build your data platforms, finally overcoming these enduring problems. You’ll learn how establishing contracts as the interface allows you to explicitly assign responsibility and accountability of the data to those who know it best—the data generators—and give them the autonomy to generate and manage data as required. The book will show you how data contracts ensure that consumers get quality data with clearly defined expectations, enabling them to build on that data with confidence to deliver valuable analytics, performant ML models, and trusted data-driven products. By the end of this book, you’ll have gained a comprehensive understanding of how data contracts can revolutionize your organization’s data culture and provide a competitive advantage by unlocking the real value within your data.
Table of Contents (16 chapters)
1
Part 1: Why Data Contracts?
4
Part 2: Driving Data Culture Change with Data Contracts
8
Part 3: Designing and Implementing a Data Architecture Based on Data Contracts

Migrating to data contracts

Now we’ve proved the concept of data contracts and started delivering some value, let’s look at how to migrate the rest of our data assets to data contracts.

We’ll need to come up with a migration plan that balances the need to complete this migration in a reasonable amount of time, so we can decommission our legacy platform and tools, against the needs of product teams to deliver against their existing roadmaps and commitments.

Unfortunately, there is no perfect way to do this, and the approach you take will highly depend on your organization and its objectives.

One good approach is to ask your key data consumers (typically data/analytics engineers and data scientists) to work together and prioritize the datasets most critical to them. This could take the form of a working group, where a few people from each team will work together on this exercise. There’s likely to be a lot of overlap, as those teams and other data...