Get In Touch
Please feel free to contact with any questions using the form below
By clicking on the button, you consent to the processing of personal data and agree to the privacy policy
CRM Marketing

Dividing the clients by loyalty with the help of RFM analysis

What RFM analysis is

RFM analysis is the analysis of the client base established on the purchase history. RFM analysis is held in three terms:
  1. Recency - recency of the purchase - time since the last purchase. The clients who bought recently are more likely to buy again.
  2. Frequency - frequency of the purchases - the amount of purchases in a given time. The probability of the sale will be higher if a person made many purchases.
  3. Monetary - the sum of purchases - the sum of all the purchases in a given period. The clients who spent a big sum of money on purchases are more likely to spend it again.
The groups of the most loyal and profitable and those of the most inactive clients are discovered as a result of the RFM analysis. Based on the RFM analysis we can build communications in a way that stimulates clients to move from one group into another, retain them and motivate them to make recurrent purchases.
RFM approach can also be used in any business, no matter the direction. Having an email list of at least 10,000 provides a clearer picture. The simplicity and clarity of the segmentation are the main advantages of this approach.

Input data for RFM analysis

To conduct RFM analysis you'll need the data on all the purchases made by all the clients and the sums of all these purchases. They are downloaded from a CRM system or an analytics platform. For example, in the projects we were RFM analyzing the information was kept in Magento.
There may appear to be some difficulty with the data. You'll probably get it in not very perfect condition, so, as a rule, you'll have to pre-process it.
You'll need to download transactions data. Every line is a separate transaction, the number of columns can be different, but there must be:
  • a unique client identifier (email, phone number, id);
  • date of purchase;
  • sum of purchase.
    Here is what the prepared data for RFM analysis might look like:

    How to conduct RFM analysis

    Step 1. Collect information by rates

    Information on every client is gathered for analysis: timespan since the last purchase (Recency), the amount of purchases (Frequency) and the sum of all purchases (Monetary).

    Step 2. Choosing the range of segmentation

    We must choose different segmentation ranges by every "Recency", "Frequency" and "Monetary" rate.
    There are three approaches to this:
    • uniform segmentation by the ranges of values;
    • uniform segmentation by the number of clients;
    • segmentation with the fixed range.

    Uniform segmentation by the ranges of values

    Division by segments in this case happens on the basis of the rates' content. You look at the dispersion of figures, logically define the amount of possible segments, take the peak figure in every rate and divide it by the number of segments.
    As a result you get segments with equal ranges on every rate:
    In our case R and F values were equally divided into 3 parts.
    1 - 214-320 days
    2 - 107-213 days
    3 - 0-106 days
    1 - 13-18 purchases
    2 - 7-12 purchases
    3 - 0-6 purchases
    The advantages of the method: segments are easy to highlight. However, if we resort to this division, the buyers classification will be lop-sided (90% of the buyers can get to one segment and only 1% into another).

    Segmentation by the amount of buyers

    In this mechanism the division by every rate is done in a way that an equal amount of buyers gets into the segments.
    This segmentation allows to quickly highlight the segments so as there is no great disbalance between the groups. The disadvantage of this approach is the low quality of segmentation.
    In this example the clients who made purchases in one day got into different segments by the Recency rate.

    Segmentation with the fixed range

    It is our favourite method. You must define the value borders for every rate on your own while segmenting with the fixed range.
    There are some nuances. When defining the range by the recency of the purchases we need to take into account:
    • seasonality;
    • the amount of time between made purchases;
    • an average client's lifetime;
    • promotions;
    • holidays.
    There is no special formula to consider them, it takes some logical thinking.
    In our example, when highlighting the thresholds, in Recency we've been referring to the average timespan between the orders and the timespan between the first and the second order. In Monetary we referred to the value of an average check. In Frequency we had to play it by the average amount of orders per person.
    We got these thresholds:
    1 - last purchase was more than 6 months ago
    2 - last purchase was 3-6 months ago
    3 - last purchase was 0-3 months ago
    1 - 1-2 orders
    2 - 3-5 orders
    3 - more than 6 orders
    While defining F we need to keep in mind that the average timespan between the first and the second and all the other orders will probably be different. A client is not yet used to the brand after the first purchase, and they will spend more time deciding to make the second one, if they decide to make it at all. And further they convert much easier.
    In our case the average timespan between the first and the second order was 53 days, and between the other ones - 36. We got this into account to highlight the newcomers' segment correctly. If we apply just the average time between the orders, the newcomers can get into the group of the developing clients and all future work with them will be built in the wrong way.
    We also need to take the seasonality and the product type for the ranges by the frequency of purchases. For example, for a beauty store, one order in two months is good, and a client with such frequency of the purchases will probably get into the segment of regular customers. And if we are talking about the grocery store, one purchase in two months is something of a random client.
    Our approach to
    calculating the loyalty program
    To define the ranges by Monetary we need to take into consideration these facts: the type of business, the price, the average check, seasonality.
    The advantage of the described method is that division is of really good quality and the clients get into their segments correctly. So working with segments will yield good results. The disadvantage is the process of segments highlighting is laborious and demands much time and specialist involvement.
    Another thing worth remembering when highlighting segments is not to forget to divide the wholesale and retail customers. The R, F, M thresholds will be different for them.

    Step 3. Organizing the segments on totality of the R, F, M rates.

    So, now we have the ranges for every rate and we need to evaluate these ranges - give them a quality coefficient. For example, it can be from 1 to 3, but the amount can be bigger depending on how detailed you want to work the segments through. 3 is just a standard number.
    We decided 1 to be the worst value and 3 to be the best. So there are 3 ratings by recency for every of the 3 rates. From the totality of the 3 rates with the same ratings we get a segment:
    • R1—F1—M(1-3) — lost;
    • R1—F(2-3)—M(1-3) — loyal clients who lost activity;
    • R2-F(1-2)-M(1-3) — idle;
    • R2-F(3)-M(1-3) — loyal idle clients;
    • R3—F1—M(1-3) — newcomers;
    • R3—F2—M(1-3) — developing;
    • R3—F3—M3 — regular.
    As a result every client is assigned to a certain segment:
    Or, for the sake of convenience we can display the same information as an interactive dashboard:
    As a result we get the RFM matrix:

    Using the RF, RM, FM matrices

    It's a rather frequent situation when building segments that pairs of the RFM analysis are used.

    RF analysis

    It is the analysis by the recency and frequency of the purchases. As monetary depends on frequency, we can sometimes just leave it out.
    Segmentation by RF shows how frequently clients make purchases per the analysed period. It allows us to highlight those clients who recently bought something and cooperate with the company.

    RM analysis

    RM analysis shows the parcelling of the clients by Recency and Monetary. Such analysis allows to highlight the clients that bring the most revenue and those whose contribution to the total profit is minor.

    FM analysis

    FM analysis shows the parcelling of clients depending on frequency and sum of the purchases. Such parcelling allows to highlight the clients who buy rarely, but spend great sums and those who make frequent purchases, but with small checks.
    This is where we leave off for now. We hope the article gave you the understanding of what RFM analysis is, what are its advantages and in what ways you can conduct it.
    Get in touch
    Tell us about your project and we will contact you for free consultation.