According to the study of Arthur Hughes, the American Institute of database marketing, customer database, there are three magic elements of these three elements constitute the best indicators of data analysis:
- The last consumption (Recency)
- Consumption frequency (Frequency)
- The amount of consumption (English Language Word or Term Chinese Language Word or Term)
RFM analysis originally used for traditional marketing, retailing and other fields, applicable to a variety of consumer goods or fast moving consumer goods industry, as long as the consumption of any data record can be used to analyze. Detailed transaction information for e-commerce sites, web site database record can also use the RFM analysis model for data analysis, especially for those who have established a customer relationship management (CRM) system sites, the results of the analysis will be more meaningful.
The basic concepts explained
RFM model is an important measure of customer value and customer profitability tools and instruments. RFM analysis model consists of three main indicators, the definition and role of these three indicators below do simple explanation:
The last consumption (Recency)
The last consumption means that the user last time buy, in theory, the last consumer more time close to the customer should be a better customer to provide real-time goods or services are most likely to have the response. Since the last consumption indicators defined a time period, and with the current time, and therefore have been changes. The most recent consumer marketing is an important indicator, it comes to attract customers, keep customers and win customer loyalty.
Consumption frequency (Frequency)
The frequency of consumption is the number of customers in a certain period of time consumption. The most commonly purchased by consumers, loyalty also, increasing the number of customers to buy means to steal market share from a competitor, the turnover earned by someone else's hands.
According to this index, we again customers divided into five equal portions, this quintile analysis is equivalent to a "loyalty ladder" (loyalty ladder was), the trick is to let consumers have been climbing down the ladder, be thought of as the sales To buy two customers to push up into three customers to buy time buyers into two.
The amount of consumption (English Language Word or Term Chinese Language Word or Term)
The amount of consumption is the most direct measure of the capacity of e-commerce website, you can also verify that the "Pareto Principle" (of Pareto's Law) - 80% of the revenue from 20% of customers.
Data acquisition and analysis
Extract relevant data from the database, you first need to determine the time span of data, according to the difference of the site sells items to determine the appropriate time span. If the operator is a fast moving consumer goods, such as daily necessities, can determine the time span for a quarter or a month; sales product turnover time is relatively long, such as electronic products, can determine the time span of one year, six months or a quarter. Can be extracted to determine the time span of data within the corresponding time interval, of which:
Last consumption (Recency) taken out of the data is a point in time, from the current point in time - the most recent consumer point in time as the measure of value, pay attention to the units of selection and unity, regardless of hours, days;
Consumption frequency (Frequency), this indicator can be directly in the database COUNT user number of the consumer;
The amount of consumption (the Monetary), the amount of consumption of each customer to the sum (SUM) obtained.
Access to the data of three indicators, the need to calculate the mean of the data for each indicator, AVG (R), AVG (F), AVG (M) to represent, respectively, and finally by three indicators of each customer to compare the mean , customers can be broken down into eight categories:
| Recency | Frequency | Monetary | Customer Type |
| ↑ | ↑ | ↑ | Important value customers |
| ↑ | ↓ | ↑ | Important developments in customer |
| ↓ | ↑ | ↑ | Important to keep customers |
| ↓ | ↓ | ↑ | Important to retain customers |
| ↑ | ↑ | ↓ | General value of customers |
| ↑ | ↓ | ↓ | General development customers |
| ↓ | ↑ | ↓ | General to maintain customer |
| ↓ | ↓ | ↓ | General customer retention |
- "↑" is greater than the mean, "↓" indicates less than the mean, thank you nancy reminder, table Recency arrow should be reversed, the following diagram is
The results show
RFM model consists of three indicators, unable to demonstrate the plane plot, so three-dimensional coordinate system used here on display, an X-axis represents the Recency, Y-axis represents the Frequency, Z-axis represents the English Language Word or Term Chinese Language Word or Term, the eight quadrants of the coordinate system, respectively, 8 category of users, according to the classification of the above table, you can use the following graphics:
RFM analysis there are some defects, it can only analyze the trading behavior of users, the users visited the site but not consumption due to the limitations of the indicators can not be analyzed, making it impossible to find potential customers. Analysis of the users of e-commerce website, due to the richness of the site data - not only have the transaction data, and can be collected from the user's browser to access the data, can be extended to a broader perspective, to observe the user, this quantitative analysis will described in detail in the analysis of the user after.
An MBA from the above part of the concept comes from the think tank Baike
»In this paper, the BY-NC-SA agreement, reproduced please specify source: The data analysis » e-commerce website RFM Analysis
Related Articles:
The last consumption (Recency)
Consumption frequency (Frequency)
The amount of consumption (English Language Word or Term Chinese Language Word or Term)
Not limited to these three indicators can be adjusted according to their own business.
Laird.zheng : Yes, to do data analysis must be combined with the site's operation mode and the specific operational characteristics.
Can not be considered, the RFM is the valuation of the user a simple version? What are the different scope of use or condition of these two methods?
The the _AT_ zhilavie : Well, the RFM was originally used in traditional sales industry, customer transaction data, e-commerce website can be more comprehensive, so the index can be done to expand, not confined to the RFM.
Understanding of the RFM earlier generation, the data base, thank you!
You are given 8 customer segmentation, I think the first category should be
Recency the Frequency the Monetary customer type ↑ ↑ ↑ important value customer why not ↓ ↑ ↑ value customers
The _AT_ nancy : Thank you, remind that Recency is the smaller the better, indeed anti-did not check my Note in the table below.
Oh, all right, you introduced me to learn a lot.
Very good ~ ~ ~ good customer analysis ideas ~ ~ learning bloggers potential customers? '
Vincent : all users to analyze the article in the blog can refer the user to analyze this directory.
RFM to use too broad, the specific use of this model when you really want to combine some of the specific features of the business, for example, different categories of users, the Monetary Recency the Frequency big difference this time we must be in accordance with the different categories RFM analysis.
Fly321283 : Well, combined with practical application in order to play a role.
The theory is simple, but I do not know how to operate and write reports.