Data analysis system can be divided into data sorting, data analysis and data presentation. Data collation includes the acquisition, screening, cleaning, collation and statistics of source data. Data collation is the preliminary processing of source data and the premise of data analysis. Data analysis is the use of data analysis tools, according to their own purposes, deep data mining and analysis, to find out the internal relations and changes; Data presentation is to present the results of analysis, mostly through professional charts, which is an important part of data analysis report, that is, the final form of data analysis. For many companies, data sorting is not difficult. The difficulty lies in how to interpret business data. How to present it to explain the problem? What business problems can be found from it? Is there any chance for improvement?

In fact, the above business problems can be transformed into analysis from three aspects. First of all, after sorting out the data, we need to look at three things: trend, distribution and comparison. Looking at the trend means looking at the time trend of the target data. Is the fluctuation big or small? Which stage has changed greatly? In which time period did the anomaly occur? The purpose of looking at the trend is to grasp the overall trend. Optional tools are: trend chart, multi-column stacked column chart;

Second, look at the distribution. Is the overall distribution of the target data segment divergent or centralized? What frequency band is it on? In which range is the median concentrated? In which data range is 80% of the data concentrated? The purpose of looking at the distribution is to understand whether the business data is stable and the concentration of the data. Optional tools are: histogram, box chart, normal distribution, bitmap, Plato.

Finally look at the contrast. More often than not, there is no problem between the chain and the year-on-year, let alone the problem, especially when the chain and the year-on-year are not much different. This time can be compared with last month to see how stable it is. Is there any change in concentration? Is there a relationship between variables? What's the connection? Optional tools include: stacked column chart, variance analysis, correlation analysis, regression analysis, etc.

Looking at the trend, distribution and comparison are the three axes of data analysis. It should be noted that data is data, and the problem still needs to be solved through specific commercial measures. Data analysis just tells you where the problem is and where the improvement is. Therefore, the three-axis interpretation results of data analysis only provide the direction to solve problems, and cannot replace specific business solutions.

These are the three skills of data analysis shared by Bian Xiao: looking at trends, looking at distribution and looking at comparison. For more information, you can pay attention to Global Ivy and share more dry goods.