Common data analysis models and methods

1. Index

In the process of data analysis, it is usually necessary to use various models to prove one's own analytical views. One is to make one's own conclusions more persuasive, and the other is to make one's own argumentation process more logical and organized.

FineBI introduced some data analysis methods to help users better use BI for data analysis.

2. RFM model

1) Overview

RFM is used to classify users and judge the value of each category of segmented users.

• Last consumption time (R): The interval between the customer and the most recent purchase time.

• Consumption frequency in the most recent period (F): Refers to the number of purchases made by customers in a limited period of time.

• Consumption money in the recent period (M): The customer's consumption ability, usually based on the customer's single average consumption money as a measurement indicator.

These three key indicators judge customer value, observe and classify customers, and carry out corresponding marketing strategies for customers with different characteristics, as shown in the following figure:

2) Implementation

The effect of FineBI is shown in the figure below:

3. Pareto analysis

1) Overview

Pareto analysis is also called ABC analysis and the core idea of classification is that a few projects contribute most of the value. Take styles and sales as an example: Style A accounts for 10% of the total, but it contributes 80% of sales.

Divide products or businesses into three categories, A, B, and C to distinguish the key and non-key business of the business, and reflect the impact of the value of each type of product on the total value of inventory, sales, cost, etc. So as to achieve differentiated strategies and management .

2) Implementation

The effect of FineBI is shown in the figure below:

4. Boston Matrix

1) Overview

The Boston Matrix analyzes and determines the product structure of a company through sales growth rate (an indicator reflecting market gravity) and market growth (an indicator reflecting corporate strength).

The Boston Matrix divides the product types into four types, as shown in the figure below:

2) Implementation

The effect of FineBI is shown in the figure below:

5. Conversion analysis

1) Overview

The conversion funnel model is a method to analyze the conversion effect of a user through a series of steps when using a certain business.

Conversion analysis can analyze the conversion and loss of various business scenarios, not only to find out the location of potential product problems, but also to locate the lost users in each link, and then target marketing to promote conversion.

2) Implementation

The effect of FineBI is shown in the figure below:

6. Shopping Basket Analysis-Association Rules

1) Overview

Everyone should have heard of such a classic case: in supermarkets, babies's diapers and beer are often sold together. The reason is that after data analysis, parents who buy diapers are mostly fathers. If they are buying diapers Seeing beer while wet, there will be a high probability of buying, thereby increasing beer sales.

This kind of analysis method that connects different commodities by studying user consumption data and digs out the links between the two is called commodity association analysis, that is, "shopping basket analysis."

Judge the association of products through the three indicators of "support", "confidence", and "lift".

2) Implementation

The effect of FineBI is shown in the figure below:

7. Analysis of repurchase rate

1) Overview

The repurchase rate refers to the number of purchases in the recent period of time, which is used to indicate the loyalty of users, and the reverse indicates the stickiness of users of goods or services.

2) Implementation

The effect of FineBI is shown in the figure below:

8. Retention analysis

1) Overview

Retention analysis is an analysis model used to analyze user participation/activity. It examines users who have performed initial behaviors. After a period of time, there are still customer behaviors (such as login, consumption).

Calculation formula: the number of new users retained in a certain period of time (period a) in another period of days (period b) / the total number of new users (period a)

2) Implementation

The effect of FineBI is shown in the figure below:

9. Inventory Turnover Analysis

1) Overview

Inventory turnover is the ratio of the cost of goods sold to the average inventory balance of an enterprise in a certain period of time, which is used to reflect the speed of inventory turnover. The higher the turnover rate, the faster the inventory turnover. The shorter the cycle from cost to commodity sales to capital return, the better the sales situation.

Inventory turnover days is the number of days that an enterprise has experienced from acquiring inventory to consumption and sales. The fewer the turnover days, the faster the inventory realization speed and the better the sales status.

2) Implementation

The effect of FineBI is shown in the figure below:

10. DuPont analysis

1) Overview

DuPont analysis method uses the relationship between several major financial ratios to comprehensively analyze the financial status of the enterprise, to evaluate the profitability of the company and the level of return on shareholders' equity, and to evaluate the performance of the enterprise from a financial perspective.

The basic idea is to decompose the return on net assets of a company into the product of multiple financial ratios, which is helpful for in-depth analysis and comparison of business performance.

2) Implementation

The effect of FineBI is shown in the figure below:

11. User portrait analysis

1) Overview

User portrait is a visual display of the data associated with the user; To sum up in one sentence: user information tagging.

By analyzing the user's demographic attributes: user's age, gender, province and city, education, marriage, fertility, industry and occupation, and behavioral characteristics: activity, loyalty and other indicators, enterprises can help users make precision marketing and assist business decisions.

2) Implementation

The effect of FineBI is shown in the figure below:

12. The YoY and chain rate analysis

1) Overview

The development speed year-on-year rate is mainly to eliminate the influence of seasonal changes and to illustrate the relative development speed of the current development level compared with the development level of the same period last year.

The chain rate represents the ratio of changes in the quantity in two consecutive statistical periods (such as two consecutive months).

Calculation formula:

Year-on-year rate: (current sales - sales in the same period last year) / sales in the same period last year

Chain rate: (current period sales - previous period sales) / previous period sales

2) Implementation

The effect of FineBI is shown in the figure below:

1) Overview

The AARRR model, also known as the pirate model, is a commonly used model in the user operation process. It explains the five indicators for achieving user growth: customer acquisition, activation, retention, revenue, and dissemination. From customer acquisition to dissemination of recommendations, the entire AARRR model forms a closed-loop model of the user's full life cycle, continuously expanding the scale of users and achieving sustained growth.

2) Implementation

The effect of FineBI is shown in the figure below: