What does a data analyst do and what skills do you need to master?

First, the basic tools.

As the saying goes, if you want to do a good job, you must first sharpen your tools, so SQL, Python, Excel, etc. are the most basic tools for data analysis, but it is not necessary to learn these to be data analysts, the work of data analysts not only needs to master some basic operations of Python and SQL, but more importantly, business knowledge architecture and data can be combined, and business problems in the process of enterprise operation can be found through various data of the enterprise, and can help enterprises solve problems.

2. Business analysis ability.

The content of the work is determined according to the company's business, and it can be roughly summarized in the following points:

To provide help to product managers, domestic product managers do not understand data analysis, and the competitive intelligence analysis of new products, product agile testing, etc. need the help of data analysts, and later product iteration optimization still needs data analysts to collect user behavior, habits, evaluation and other data to complete.

Formulate standards for the company's data, connect the data of various departments, and realize data management.

3. Ability to communicate, collaborate and solve problems.

Any enterprise needs a data analyst, the core of his work is to solve problems for enterprises through data, it is an important hub of enterprises, connecting the company's products and operations and other departments, and plays a vital role in enterprises, which requires very strong logical thinking skills and communication skills, and all aspects of communication are in place in order to efficiently solve problems for enterprises.

In addition, from the current experience and observation, most of the data analysts in the society lack business knowledge, and have little project experience, which is difficult to meet the needs of enterprises.

Working hard in the big city, going out early and returning late every day, catching the bus and squeezing the subway, 3 5 of our life time is spent on the road and work, except for sleep, the spare time that really belongs to us is really very little. Therefore, if you want to learn data analysis efficiently, it can be regarded as the improvement of personal professional skills and pave the way for future job hopping or career change. However, how do you plan your learning time clearly so that you can master the basic skills of data analyst step by step?

It's a good thing to think about and plan well.

In general, the basics are learned first, then the theory, and finally the tools. Basically, every language is learned in this order.

1. Learn the basic knowledge of data analysis, including probability theory and mathematical statistics. The foundation still needs to be mastered, the foundation is not yet solid, and the knowledge edifice is very easy to collapse.

2. Relevant theoretical knowledge of your target industry. For example, if you are in finance, you must learn various knowledge such as **, banking, and finance, otherwise you will be confused when you arrive at the company.

3. Learn data analysis tools, software combined with the practical application of cases, and the mainstream software for data analysis is (from easy to difficult): excel, spss, stata, r, python, sas, etc.

4. Learn how to operate these software, and then use the software to process and analyze the data step by step, and finally output the results, test and interpret the data.

Data analysts need to take courses in the following areas:

1) Data management.

a. Data acquisition.

Enterprise requirements: database access, external data file read.

Case Study: Using a Product Information File to Demonstrate Data Read-In Synergy with SPSS.

b. Data management.

Enterprise needs: Encode, clean, and transform large data.

Case Study: The Process of Using the Bank Credit Default Information File SPSS.

1) Data selection, merging and splitting, and checking for outliers.

2) New variable generation, spss function.

3) Transform data structures using SPSS – transpose and reorganize.

4) Commonly used descriptive statistical analysis functions. Frequency process, description process, exploration process.

c. Data exploration and report presentation.

Enterprise needs: Exploration of enterprise-level data, primarily involving the use of graphs. SPSS report output.

Case study: Business performance documents, how to generate beautiful and clear reports.

1) Check the variables before making the report.

2) Make reports for different types of data processing.

3) The difference between the report generation feature and other options.

2) Data Processing.

a. Correlation and difference analysis.

b. Linear**.

Business Needs: Explore the factors that affect business efficiency and further improve business efficiency.

Case Study: Analysis of the influencing factors of product qualification rate and its ** analysis.

c. Factor analysis.

Enterprise needs: It is necessary to extract the main factors that affect the efficiency of enterprises and make key investments.

Case Study: Customer Purchasing Power Information Research.

d. Cluster analysis.

Business needs: Need to know the information of the customers who are buying the product.

Case Study: Customer Purchasing Power Information Research Lingqi Chaos.

e、bootstrap。

Case Study: Bootstrap Sampling.

3）spss**。

SPSS application.

1. Understand business. The premise of engaging in data analysis will need to understand the business, that is, familiar with industry knowledge, the company's business and process, it is best to have their own unique insights, if they are separated from the industry cognition and the company's business background, the result of the analysis will only be a kite off the line, without much use value.

2. Understand management. On the one hand, it is the requirement to build a data analysis framework, for example, to determine the analysis idea, it is necessary to use marketing, management and other theoretical knowledge to guide, if you are not familiar with management theory, it is difficult to build a data analysis framework, and it is difficult to carry out follow-up data analysis. On the other hand, it is used to provide instructive analysis suggestions for the data analysis conclusions.

3. Understand analysis. It refers to mastering the basic principles of data analysis and some effective data analysis methods, and being able to flexibly apply them to practical work in order to effectively carry out data analysis. The basic methods of analysis are:

Comparative analysis, group analysis, cross-analysis, structural analysis, funnel analysis, comprehensive evaluation and conjecture analysis, factor analysis, matrix correlation analysis, etc. Advanced analysis methods include: correlation analysis, regression analysis, cluster analysis, discriminant analysis, principal component analysis, factor analysis, correspondence analysis, time series, etc.

4. Understand tools. Refers to mastering the common tools related to data analysis. Data analysis method is theory, and data analysis tools are tools to realize the theory of data analysis methods, in the face of more and more huge data, we can not rely on calculators for analysis, we must rely on powerful data analysis tools to help us complete data analysis work.

5. Understand design. Understanding design refers to the use of charts to effectively express the analytical views of data analysts, so that the analysis results are clear at a glance. The design of charts is a major matter, such as the selection of graphics, the design of layouts, the matching of colors, etc., all of which need to master certain design principles.