Store Manager's Job: Customer Management Part 3 - Data Analysis

Regarding customer management, we covered the basics in Part 1 and how to collect data in Part 2, so now it is finally time to perform a simple analysis of the data we have collected.

We will start with the basic data mentioned in Part 2: customer name, purchase date (number of transactions), number of items purchased, purchase amount, and product category.

* Is the number of new customers increasing, or is it stagnant?

* Has the number of transactions decreased?

These are the first items to check.

This is because even if sales are growing, if the number of customers is decreasing, future growth cannot be expected.

* What is the repeat rate?

You can determine how many people are returning by dividing the number of customers who have visited multiple times by the total number of customers. If this number is high, it means you have the support of your customers.

* Check the average spend per customer and purchase frequency.

Average spend per customer also includes the unit price per item and the unit price per transaction. This tells you whether many cheap items are being sold or if expensive items are sold only occasionally. The unit price per item is calculated by dividing sales by the number of items, and the unit price per transaction is calculated by dividing sales by the number of transactions.

Purchase frequency can be calculated by dividing the number of visits by the number of customers.

This tells you whether customers tend to buy expensive items occasionally or make small purchases frequently.

You can then tailor your approach to these trends.

* Identify your top customers by sales.

You can see this by sorting customers in descending order of sales.

According to the commonly cited "80/20 rule," the top 20% of customers account for 80% of total sales. These customers are your VIPs and must be treated with care.

* Investigate dormant customers.

By using Excel to check how many days have passed since the most recent purchase, you can identify customers who have not visited for a long time.

Knowing this allows you to take measures such as sending direct mail to remind them of your store.

These are the basics of RFM analysis, which is a common analytical method. RFM analysis is a method of classifying customers by scoring them from 1 to 5 on R: Recency (have they purchased recently?), F: Frequency (are they a repeat customer?), and M: Monetary (are they contributing to sales?). Customers with high R, F, and M scores are classified as loyal customers; customers with high R but moderate F and M are repeat customers; customers with low R but moderate F and M are dormant customers; and customers with high R but low F and M are classified as new customers.

Additionally,
LTV Analysis: A method to estimate how much profit a customer will generate over their lifetime, calculated as average purchase price × average purchase frequency × profit margin.

This serves as data to help determine how much to invest in that customer segment.

Cohort Analysis: By grouping customers based on their first purchase month, etc., you can see which month's acquired customers are more likely to be retained based on subsequent trends.

Basket Analysis: By examining products purchased together as add-ons, you can make adjustments to encourage more purchases.

Churn Analysis: This refers to attrition analysis, where you identify customers whose visit frequency has suddenly dropped and encourage them to return via email or direct mail.

It also seems possible to use tools to predict the next likely products to sell or days that are likely to be busy.

By analyzing in this way, it becomes clear who to approach and how.

And so, you can take measures to keep loyal customers, minimize the number of customers leaving, and accurately seize sales opportunities to lead to increased revenue.

Now, next time, let's look at how to utilize the analysis results.

Thank you for reading.
I would appreciate it if you could like and follow.
I look forward to your continued support.

#WhatIs