Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
53 views

RFM Analysis Using Python Spark

This document discusses RFM analysis, a marketing technique that quantitatively ranks customers based on recency, frequency, and monetary value of their transactions. It describes the RFM metrics of recency, frequency, monetary value and how customers are segmented into groups like loyalists, potential loyalists, new customers, and at-risk customers. The methodology section explains how customers are scored and ranked, and the dataset required for RFM analysis is outlined, including fields like customer ID, order number, sale price, and date.

Uploaded by

adyatma ardi
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
53 views

RFM Analysis Using Python Spark

This document discusses RFM analysis, a marketing technique that quantitatively ranks customers based on recency, frequency, and monetary value of their transactions. It describes the RFM metrics of recency, frequency, monetary value and how customers are segmented into groups like loyalists, potential loyalists, new customers, and at-risk customers. The methodology section explains how customers are scored and ranked, and the dataset required for RFM analysis is outlined, including fields like customer ID, order number, sale price, and date.

Uploaded by

adyatma ardi
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

RFM ANALYSIS USING SPARK PYTHON

Achmad Adyatma Ardi1


Programmer, Data Scientist, Engineer
*Corresponding author : achmad541997@gmail.com
Saturday, April 23, 2022

Abstract

With good knowledge and good tools to analyze the data, datas can tell you
everything you want. Programming languages is good one for this purposes. In this
research, I will show you how to visualize data using python. The data set used is
weather data contained 14 variables to analyze. To execute programming statement
we use Jupyter Notebook. Kind of visualization data using seaborn library include :
barplot, displot, joinplot, pairplot, stripplot, swarmplot, boxplot, countplot, pointplot,
lmplot

Keyword : data science, python programming, visualize data, seaborn library,


pandas library, jupyter notebook

Introduction
customers who recently made a
RFM analysis is a marketing purchase will still have the product
technique used to quantitatively rank on their mind and are more likely
and group customers based on the to purchase or use the product
recency, frequency and monetary total again. Businesses often measure
of their recent transactions to identify recency in days. But, depending on
the best customers and perform the product, they may measure it in
targeted marketing campaigns. years, weeks or even hours
RFM analysis ranks each 2. Frequency
customer on the following factors It means the frequency of customer
called (RFM Metrics): transactions. How often did this
1. Recency customer make a purchase in a
It means the freshness of customer given period ? customers who
activity. How recent was the purchased once are often are more
customer’s last purchase ? likely to purchase again.

Achmad Adyatma Ardi


Additionally, first time customers They are your recent customers
may be good targets for follow – with average frequency and who
up advertising to convert them into spent a good amount. Offer
more frequent customers membership or loyalty programs or
3. Monetary recommend related products to
It means the willingness to spend. upsell them become your loyalists
How much money did the or champions.
customer spend in a given period ? 3. New customers
customers who spend a lot of They are your customers who have
money are more likely to spend a high overall RFM score but are
money in the future and have a not frequent shoppers. Start
high value to a business building relationships with these
customers by providing
RFM analysis is a powerful tool onboarding support and special
in marketing that helps marketers offers to increase their visits.
make the best of their advertising 4. At risk customers
budget. Also, nonprofits and charities They are your customers who
can user RFM analysis to find the best purchased often and spent big
donors, for example as those who have amounts, but havent’t purchased
donated in the past are more likely to recently. Send them personalized
donate again in the future. reactivation campaigns to
Instead of simply using an reconnect, and offer renewals and
overall RFM average value to identify helpful products to encourage
the best customers, RFM analysis can another purchase
be used to identify clusters of 5. Can’t lose them
customers with similar values called They are customers who used to
customer segmentation. These are kind visit and purchase quite often, but
of customer : haven’t been visiting recently.
1. Loyalist / Champions Bring them back with relevant
They are the best customers, who promotions, and run surveys to
bough most recently, most often, find out what went wrong and
and are heavy spenders. Reward avoid losing them to a competitor.
these customers. They can become
early adopters for new products Methodology
and will help promote your brand.
2. Potential loyalists RFM analysis scores customers
on each of the three main factors.

Achmad Adyatma Ardi


Generally, a score from 1 to 5 is given,
with 5 being the highest. Various
implementations of an RFM analysis
system may use slightly different
values or scaling.
The collection of three values for
each customer is called an RFM cell.
In a simple system, organizations
average these values together, then sort
customers from highest to lowest to
find most valuable customers. Some
businesses, instead of simply
averaging the three values, weight the
values differently

RFM Dataset Required

To do RFM analysis, the


required data are :
1. SKU – Stock Keeping Unit. A
unique product code
2. OrderNum – order number (i.e.,
transaction id)
3. CustomerID – unique customer id
4. Sale Price – sold price (what the
customer has paid for the item
bought in the order)
5. SKU Description – description of
the product
6. Created On – the date on which the
customer has created the order
7. Category – the category of the
product (SKU). There are consists
of several category based on SKU

Achmad Adyatma Ardi

You might also like