The Difference and Connection between Big Data Analysis and Data Analysis

Big data analysis and data analysis are different and connected. The focus here is on the differences and connections between the two in terms of technical requirements, usage scenarios, and business scope. The key point is to distinguish the difference and connection between theoretical research and practical application.


What is data analysis?

Data analysis refers to the process of analyzing a large amount of collected data with appropriate statistical analysis methods, without extracting useful information and forming conclusions, to study the data in detail and summarize the process.

Data analysis includes two aspects: "data" and "analysis". On the one hand, it includes mobile phones, processing and collating data, and on the other hand, it also includes analyzing data, extracting valuable information from it and forming useful conclusions for the business.

The results of data analysis are usually presented in the form of analysis reports. For data analysis reports, analysis is the argument, data is the argument, and both are indispensable.

Three similarities and differences between traditional data analysis and big data analysis:

First, there is no essential difference between the two in terms of analysis methods.

The core work of data analysis is human analysis, thinking and interpretation of 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 needs to be statistically processed in accordance with the analysis ideas, and summary statistical results are obtained for analysis. The two are similar in this process, the difference is only the processing method caused by the size of the original data.

Second, there is a big difference between the two in the use of statistical knowledge.

The knowledge used in "traditional data analysis" mainly revolves around the theme of "Can we infer the real world through a small amount of sampled data". "Big data analysis" mainly uses various types of full data (not sampled data) to design statistical programs and obtain detailed and reliable statistical conclusions.

Third, in relation to the machine learning model, there are essential differences between the two.

"Traditional data analysis" most of the time, knowledge uses machine learning models as black box tools to assist in data analysis. And "big data analysis" is more often a close combination of the two. Big data analysis produces not only an analysis effect evaluation, but subsequent upgrades based on this. In the scene of big data analysis, data analysis is often a prelude to data adding ink, and data modeling is the result of data analysis.