Skip to main content

Table 3 CRISP-DM framework - stages

From: Towards decision analytics in product portfolio management

Stage Description
Business understanding phase Focuses on understanding the project objectives and requirements from a business perspective, converting this knowledge into a data mining problem definition and a preliminary plan is designed to achieve the objectives (Chapman, et al., 2000)
Data understanding phase The initial data collection and proceeds with activities to get familiar with the data, discover quality problems and insight (Chapman, et al., 2000)
Data preparation phase Covers all activities needed to construct the final data set (Chapman, et al., 2000).
Modeling phase The selection and application of modeling techniques. Typically, several techniques are available for the same data mining problem type. Some techniques have specific requirements regarding the structure of the data. Therefore, going back to the data preparation phase is often necessary (Chapman, et al., 2000).
Evaluation phase The evaluation of the created data mining models, before actually deploying them. By thoroughly evaluating and reviewing the steps used to create the model it is determined if the model achieves the business objectives. If not, a new iteration of the modeling phase is started (Chapman, et al., 2000).
Deployment phase The implementation of the results found by the data mining model within the supplied data set via tools such as reports or dashboards (Chapman, et al., 2000)