Home The Blog Agile Business Analytics, not just Agile DW development

Nov 15
2008

Agile Business Analytics, not just Agile DW development

Posted by Michael McIntire in generalefficiencycostagile

Today I ran across some discussion about Agile Development in Data Warehousing, and note that we talk about this in the context of the DW development, but not in relation to the Business. I believe there is a need to discriminate some of these processes quite differently. Most simply put - One is applying Agile to DW development; the other is applying Agile to Business Analysis.

Core DW foundations involve modeling root components of business data needs and implementing a data model which allows for flexibility to answer questions of the data - a concept I call "Designing for the Unknown". The more renormalization and change from the source system, typically the more transformation logic and less flexibility, and ergo higher cost and less organizational agility.

Effective Agile development of the DW infrastructure itself involves delineating the methodologies which can be used for what types of development functions. For example, creating a core or "root key" entity in the data model requires much more extensive development than adding non-root entities or attributes, which can utilize a speedboat type process. Anything which involves the generation of system assigned keys, or creates system of record issues is not a candidate for rapid development because of the organizational and communications dependencies and requirements.

Then the more important question becomes: Have you built technology and Infrastructure which enables the business to quickly and accurately make decisions. Have you made your business Agile? Assuming you get the core DW development right, and there is a substantial enough set of generalized data in one place, then you can enable Business Agility with Sandboxes (see Brobst et al). Does your DW support the analysis of non-core data purchased by your business? Can you do this the same day, or does it take 90 to 180 days to use one time data because the Product Development Life Cycle requires it?

Agile in relation to DW is less about applying Agile to the development of the DW infrastructure, and more about making THAT infrastructure capable of enabling Agile decision making - which is the whole point of an Analytics Infrastructure like DW in the first place...


Hits: 27304
Trackback(0)
Comments (0)add comment

Write comment

busy

Tags

We have 49 guests online