An intro to the CRISP-DM Methodology
A series on Cross-Industry Process for Data Mining
Use the CRISP-DM methodology when you need to extract value from data and accelerate the adoption of advanced analytics.
By the end of this blog, you will…
- Be able to define CRISP-DM Methodology and when it’s applicable.
- See a high-level overview of the CRISP-DM steps.
What is the CRISP-DM Methodology?
CRISP-DM is used to discover previously unknown patterns and knowledge in data. The CRISP-DM methodology is practical, flexible and useful when solving business issues with analytics.
“The CRISP-DM methodology provides a structured approach to planning and executing a data mining project.” — Smart Vision Europe
With this method, you can solve analytics issues to architect practical solutions that solve day-to-day business problems. There are six major steps for applying the CRISP-DM methodology, shown in the diagram below:
- Business Understanding
- Data Understanding
- Data Preparation
- Modeling
- Evaluation
- Deployment
Each step from the CRISP-DM Process can be completed in any order and you may find yourself repeating portions. Over the next six weeks, I plan to update and hyperlink a deeper dive associated with each of the steps listed above to a new blog.
The CRISP-DM methodology does not define all possible routes for your Data Mining process but it is very helpful.
In this blog, we have…
- Defined the CRISP-DM Methodology
- Seen where it’s appropriate to use it.
- Gotten a sense of the steps from a high-level overview.
In the coming weeks, I will be doing a deeper dive on the six steps in the CRISP-DM Methodology.
Sources:
………………………………………………………………………………………
The CRISP-DM Methodology, not to be confused with Kia Shine’s Kris-py.