rfm-analysis
# What is RFM?
Are all my customers similar?
What differentiated them from each other?
Who is the most likely customer?
Who are my best customers?
Which customer has the potential to buy more?
Which customer has been churned out / has lapsed?
Which customer can be converted by creating value through promotions?
Which customer is likely to be loyal in the near future?
What brand means the existing customers?
Summary:
- Built on historical transactions between user and the business
- Uses R, F, and M variables of customer data
- Analyses the entire population
- No need to create curated sample sets
- Dependent on efficient and accurate data
- No scope for human error
Goals:
- Help businesses differentiate between marketing to existing and new customers
- Helps them create relevant and personalized messaging by understanding user behavior
- Help businesses magane customer perceptions
- Segment it’s customers based on three criteria, based on an existing customer’s transaction history
- Prevent churn by using fundamental marketing principles of segmentation, targeting, and positioning
- Translate positive sentiment into purchase opportunities
- Allow us to devide potential customer groups, allowing business to talk to them separately
Pareto principle to RFM:
- 80% of total results are driven by the top 20% causes
- In marketing: 80% of your total sales are likely to come from your top 20% of customers
Why customer segmentation is highly critical
- Regular customers will always be high contributors to business monetary value, and hence that customer
All R, F, M criteria can be graded on a scale of 1 to 5. It is also critical to specify an appropriate range for each grade, in order to create a customer group with a similar or a particular behavior
# Recency
How recenly the user interacted with the website/app?
When was the last time your cusotmer purchased a product/service?
Example: Days since last purchase/visit
Interpretation:
- High recency: Customer has positively considered your brand for a purchase decision recently
How to calculate:
- Can be scored by grading on custom-built filters such as bought on the last days / 1 month / 3 months and so on, depending on the nature of the business
# Frequency
How frequently the user interact
Example: Total number of days when a purchase/visitt was done
Interpretation:
- High frequency: Customer buys your brand frequently and id likely to be a loyalist of your brand
How to calculate:
- Business need to analyze the total number of purchases completed by customers in a fixed time period
- Scored by grading on custom-built filters such as bought thrice in a year / bought once a month and so on, depending on the nature of the business
# Monetary
How much do they spend?
Example: Customer lifetime value
Interpretation:
- High monetary value scores: A customer is the highest purchase history of your brand
# Advantages
Why is RFM analysis is better than traditional segmentation model?
The RFM analysis built on transactions between the customer and the business, to create a robust data-backend method based on hard numbers
This customer data is graded, analyzed, and then segmented in order to engage customers as distinct groups.
This model helps businesses effectively analyze the past buying behavior of each customer, to predict and shape future customer behavior
# Difference between RFM and traditional segmentation methods
Traditional methods:
- Traditional methods of customer segmentation, used by market research companies before the advent of data analytics, used variables like demographic and psychographic factors to group their customers
- A sample could be incorrect, due to many reasons like an insufficient number of consumers, incorrect gender balance, varying psychigraphic factors, etc
- Traditional research involved factors like psychographics, which could be interpreted subjectively