We must devise a series of steps to analyze consumption.We must estimate the resources needed when generating electricity.This final step helps us create an initial process plan and estimate the effort and resources needed to achieve our goals. We must find out what type of problem it is - Classification, Prediction, or Clustering?.We must use data mining techniques to find what other factors affect consumption.This step helps us identify how to translate the business goals into data mining goals and select a proper way for its assessment. One major factor affecting it is temperature. We must find out the factors that affect the increase in electricity consumption.This step helps us analyze the project’s current situation by identifying the resources and the stakeholders of the project. This step helps us define the necessary methods to be taken when considering a business as a success.įor our problem, our objective is to “Predict the approximate electricity consumption for the next day, to allocate necessary resources”. Now, let’s understand this from the perspective of our problem statement. How is the success of the project measured?.This step focuses on understanding the objectives of the project and requirements from the perspective of the business. Steps in CRISP-DM Understanding the problem statement Let’s devise a solution to predict the next days’ electricity consumption. Now that we have understood what’s the business problem. To understand CRISP-DM methodology, let’s look at a simple case study.Ī utility company wants to predict the next days’ demand for electricity, to allocate necessary resources for power generation. A significant increase in the usage of this methodology can be seen after conducting a poll in 20, as shown in the below image:Īccording to Wikipedia, “Data mining is a process model that describes commonly used approaches that data mining experts use to tackle problems… it was the leading methodology used by industry data miners.” What is CRISP-DM?Īccording to this article, CRISP-DM stands for CRoss-Industry Standard Process for Data Mining and was developed in 1996.ĬRISP-DM is one of the most preferred techniques used to build data mining projects. With the increase in the projects’ complexity, it is recommended to follow a standard framework to achieve goals faster. Encouraging best practices used for achieving better results.Improving project planning and management.Recording experience, which can be later used in replicating it for other similar projects.The use of a standard framework helps us in: With the rise in usage of data mining across several industries, the need for a standard framework is required to achieve the project’s objectives. As a prerequisite, you must have a beginner level understanding of how data science projects are built. We’ll be studying a case study to understand how this methodology has helped data scientists build successful projects. We will also get an overview of how it can be used by analyzing a case study. This article will cover how the CRISP-DM methodology can be used to build successful data science projects.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |