About data analysis methodology

This is an article about data analysis methodology.

hello!

Today we will learn about data analysis methodology.

Data analysis methodology refers to methods and procedures for systematically carrying out the process of collecting, cleaning, and analyzing data to derive useful insights.

There are a variety of data analysis methodologies, let’s take a look at some of the most representative ones.

CRISP-DM (Cross-Industry Standard Process for Data Mining)

CRISP-DM is a process for data mining and analytics projects that consists of the following steps: business understanding, data understanding, data preparation, modeling, evaluation, and deployment.

This methodology is widely used in practice and has iterative and complementary characteristics.

KDD (Knowledge Discovery in Databases)

KDD is a methodology that describes the process for extracting knowledge from large-scale data, and includes processes such as data selection, preprocessing, transformation, data mining, and interpretation.

It was widely used as an early methodology in data mining.

TDSP (Team Data Science Process)

TDSP is a process for data science projects and consists of the following steps: business understanding, data collection, modeling, deployment, and maintenance.

It is a methodology that specifically focuses on helping data science teams collaborate to carry out projects.

Bayesian Methods

Bayesian methodology is a methodology that deals with uncertainty through probabilistic inference and probability modeling, and is used for decision-making by updating prior information with posterior inference.

Machine Learning Methods

Machine learning methodology is a methodology that learns patterns from data and builds predictive models. There are various methodologies such as supervised learning, unsupervised learning, and reinforcement learning.

Conclusion

As above, these data analysis methodologies provide guidelines for systematically performing data science and analysis projects, and help extract meaningful information from data and use it for decision-making.

thank you!