Data mesh

Data mesh is a sociotechnical approach to building a decentralized data architecture by leveraging a domain-oriented, self-serve design (in a software development perspective), and borrows Eric Evans’ theory of domain-driven design ^[1] and Manuel Pais’ and Matthew Skelton’s theory of team topologies.^[2] Data mesh mainly concerns itself with the data itself, taking the data lake and the pipelines as a secondary concern. ^[3] The main proposition is scaling analytical data by domain-oriented decentralization.^[4] With data mesh, the responsibility for analytical data is shifted from the central data team to the domain teams, supported by a data platform team that provides a domain-agnostic data platform.^[5] This enables a decrease in data disorder or the existence of isolated data silos, due to the presence of a centralized system that ensures the consistent sharing of fundamental principles across various nodes within the data mesh and allows for the sharing of data across different areas.^[6]

The term data mesh was first defined by Zhamak Dehghani in 2019^[7] while she was working as a principal consultant at the technology company Thoughtworks.^{[8] [9]} Dehghani introduced the term in 2019 and then provided greater detail on its principles and logical architecture throughout 2020. The process was predicted to be a "big contender" for companies in 2022.^{[10] [11]} Data meshes have been implemented by companies such as Zalando,^[12] Netflix,^[13] Intuit,^[14] VistaPrint, PayPal ^[15] and others.

In 2022, Dehghani left Thoughtworks to found Nextdata Technologies to focus on decentralized data.^[16]

Data mesh is based on four core principles:^[17]

• domain ownership;
• data as a product;
• self-serve data platform;
• federated computational governance.

In addition to these principles, Dehghani writes that the data products created by each domain team should be discoverable, addressable, trustworthy, possess self-describing semantics and syntax, be interoperable, secure, and governed by global standards and access controls.^[18] In other words, the data should be treated as a product that is ready to use and reliable.^{[19] [20]}

After its introduction in 2019^[7] multiple companies started to implement a data mesh^{[12] [14] [15]} and share their experiences. Challenges (C) and best practices (BP) for practitioners, include:

C1. Federated data governance

Companies report difficulties to adopt a federated governance structure for activities and processes that were previously centrally owned and enforced. This is especially true for security, privacy, and regulatory topics.^{[21] [22] [23]}

C2. Responsibility shift

In data mesh individuals within domains are end-to-end responsible for data products. This new responsibility can be challenging, because it is rarely compensated and usually benefits other domains.^{[21] [22]}

C3. Comprehension

Research has shown a severe lack of comprehension for the data mesh paradigm among employees of companies implementing a data mesh.^[21]

BP1. Cross-domain unit

Addressing C1, organizations should introduce a cross-domain steering unit responsible for strategic planning, use case prioritization, and the enforcement of specific governance rules—especially concerning security, regulatory, and privacy-related topics. Nevertheless, a cross-domain steering unit can only complement and support the federated governance structure and may grow obsolete with the increasing maturity of the data mesh.^{[21] [24]}

BP2. Track and observe

Addressing C2., organizations should observe and score data product quality as tracking and ranking key data products can encourage high-quality offerings, motivate domain owners, and support budget negotiations.^[21]

BP3. Conscious adoption

Organizations should thoroughly assess and evaluate their existing data systems, consider organizational factors, and weigh the potential benefits before implementing a data mesh. When introducing data mesh, it is advised to carefully and consciously introduce data mesh terminology to ensure a clear understanding of the concept (C3).^[21]

Scott Hirleman has started a data mesh community that contains over 7,500 people in their Slack channel.^[25]

• Data product
• Data management
• Data platform
• Data vault modeling, method of data modeling with storage of data from various operational systems and tracing of data origin, facilitating auditing, loading speeds and resilience
• Data warehouse, a well established type of database system for organizing data in a thematic way
• ETL and ELT

• Databases

• CS1 maint: location missing publisher
• Articles with short description
• Short description matches Wikidata
• Wikipedia articles that are too technical from January 2023
• All articles that are too technical