A data warehouse is a central data storage system designed to encompass all data across the enterprise. It is a topic-oriented, integrated, time-dependent and non-volatile collection of data. It supports the decision-making process of management levels by providing a coherent view of all enterprise-wide data.
It is an architectural blueprint, more precisely a logical (intangible) concept. The DWH architecture is usually integrated and realised via several, dependent database systems. The goal of DWH is to bundle all of an organisation's data into one system. However, it is not uncommon for companies to maintain multiple DWHs, depending on their size. The characteristics of a DWH are:
- Integrated: A data warehouse architecture integrates data from multiple data sources that are otherwise distributed across (or beyond) an organisation.
- Topic-oriented: The aim is to provide its users with a view of specific subject areas, e.g. "sales", and to analyse them.
- Time-dependent: DWHs store accumulating data permanently. This contrasts with transactional systems, which only store the most recent records.
- Non-volatile: The goal of a DWH is to store data continuously to provide a picture of what has happened, not to change that picture. Therefore, once data is stored in the DWH, it typically does not change.
For decades, data warehouse architectures were the architectural solution of choice for how data should be moved and stored in an organisation.
The goal of a DWH is to organise the movement of data in a company, from its collection to its use; to ensure this, it is a unified, centralised solution that stores all the data present in a company.