Suppose you want to remarket your users for conversions and reactivations by creating segments based on their website app activities using the google analytics data stored in BigQuery.
In this guide, I will show how to implement one of the popular techniques to segment users, and visualize the results to help make important marketing decisions.
The technique we will go through is RFM analysis. We will be using BigQuery ml to create segments and the data studio to visualize the results. Here is how it will look.
The dashboard of segmented users, by Muffaddal
In this guide we will:
First, **calculate the recency, frequency, **and **monetary **value of users.
Second,** create** **customer segments using k-means clustering **algorithm.
Third, visualize the results in the data studio.
Fourth, import** RFM-analysis results to Google Analytics **for activations
Fifth, automate RFM analysis process.
Note: if you are interested in exploring more of such techniques in GCP here is a good course from Google to start with.
What is RFM Analysis?
One of the customer segmentation strategies is to create user cohorts using RFM analysis. It is based on the user’s past activities. It uses three metrics to perform segmentation:
- Recency: Number of days since last purchase.
- Frequency: Number of times the user purchased.
- Monetary: Total amount user spent on the purchase.
Mainly used for purchases but RFM analysis can also be tailored to use for other important user activities such as the number of pages viewed instead of the number of times purchased for a content-based business like medium.com.
Benefits
The benefit of RFM analysis is that since users were segmented based on their past activities we have a pretty good idea about their affinity towards the business and each segment can be targeted accordingly.
So as an example a user who frequently purchases from the website, and his average purchase amount is also high we instantly know that this is a loyal customer and should be used to spread the word of mouth. While on the other hand a user segment who had recently purchased but is not frequent can be offered a discount offer to help him get used to the product more.
#machine-learning #bigquery #segmentation #marketing #analysis #data analysis
