CRISP-DM Phase 5: Evaluation Phase
This is part 6 of the 7-part series’ summary explanation of the openSAP’s 6-week Getting Started with Data Science (Edition 2021) course by Stuart Clarke. Part 5 is here.
Part 5 Recap
In the fifth part of this series, I briefly explained how to choose a model, what are the available models to use, and the difference between a Parametric vs. Non-Parametric Machine Learning Models.
There are six phases of CRISP-DM with particular tasks and output:
Six phases of CRISP-DM:
- Business Understanding
- Data Understanding
- Data Preparation
- Modeling
- Evaluation
- Deployment
In this article, we will focus on the fifth phase which is Evaluation Phase. After choosing and running the model, we need to evaluate the results to determine if there is some reason why this model will not work and also justify why this model is appropriate to use.
Note: I will not be covering each model and how it works under the hood. To know more about each different types of model, how it works, and how to evaluate them, you can enroll here: openSAP’s 6-week Getting Started with Data Science (Edition 2021) course.
In the process flow above, Evaluation phase is broken down into three main tasks together with its projected outcome or output in detail.
Simply put, the Evaluation phase’s goal is to:
- Evaluate Results by assessing the degree to which model meets objective of the business and testing the models on test applications if time and budget permits.
- Review Process by conducting a more thorough review of the data mining engagement to determine if there is any important factor or task that has somehow been overlooked during the process, identify any quality assurance issues, and summarize the process review and highlight activities that have been missed and/or should be repeated.
- Determine next Steps by assessing how to proceed with the project. In this part, listing potential further actions along with the reason for and against each option and describing how to proceed is important.
In the next part, we will talk about the last phase which is the Deployment Phase. If you are working on a data science project for your company or even personal project/s, try to apply the above steps if applicable. As again, different data science projects have different sets of requirement. The CRISP-DM methodology just serves as a template to ensure you have considered all of the different aspects specific to your project.
References:
