Connection and difference between data description and data analysis

There are differences and connections between big data analytics and data analytics. The focus here is on the two is the technical requirements, the use of the scene, the scope of business and other aspects of the difference and connection. The focus should be to distinguish between theoretical research and practical application of the two aspects of the difference and connection.

What is data analysis?

Data analysis refers to the use of appropriate statistical analysis of a large amount of data collected for analysis, not to extract useful information and form conclusions on the data to the detailed study and summarize the process.

Data analysis includes "data" and "analysis" of two aspects including cell phones, processing and organizing data on the one hand, on the other hand, also includes analyzing the data, from which to extract valuable information and form conclusions that will help business.

The results of data analysis are usually presented in the form of an analysis report. For a data analysis report, the analysis is the thesis and the data is the argument, both of which are indispensable.

Traditional data analysis and big data analysis of the three similarities and differences:

First, in the analysis method, the two are not essentially different.

The core work of data analysis is to analyze, think and interpret the data indicators, the amount of data that the human brain can carry is extremely limited. Therefore, whether it is "traditional data analysis" or "big data analysis", the original data need to be analyzed in accordance with the idea of statistical processing, to get a summary of the statistical results for human analysis. Both are similar in this process, the difference is only the size of the raw data caused by the different processing methods.

Secondly, there is a big difference between the two in terms of the focus of the use of statistical knowledge.

Traditional data analytics uses knowledge centered around the theme of "whether the real world can be inferred from a small sample of data". "Big Data Analytics focuses on utilizing all types of full-volume data (not sample data) to design statistical scenarios that lead to statistical conclusions with both detail and confidence.

Third, there is a fundamental difference in the relationship with machine learning models.

Traditional data analytics, for the most part, uses machine learning models as black-box tools to assist in analyzing data. The "big data analysis", more often than not, is a close combination of the two, big data analysis output is not only an analysis of the effectiveness of the evaluation, follow-up based on this to upgrade the product. In the big data analysis scenario, data analysis is often a prelude to data inking, data modeling is the results of data analysis.