Defining churn
A good definition is the one from Investopedia: "The churn rate, also known as the rate of attrition or customer churn, is the rate at which customers stop doing business with an entity." You can compare churn with the leaky bucket problem. You can fill the bucket with more water (or new customers in this case), but your overall revenue won't increase if existing customers are leaving your company. It's easier to retain customers than to attract new customers, so for many companies it's a priority to reduce churn..
- PowerBI Desktop
- DAX Language
- Windows 10 (21H2)
2.Create churned column to convert churn status into binomial for the ease of analysis instead of (yes,no) structure using (IF). Then create a measure with the number of churned_customers to find the churn rate.
3.Next a bar chart is created to represented the different reasons that causes customers to churn
4. Reasons that cause customers to churn are categorized into four distinct churn categories. For example, reasons related to other competitors, attitude…etc.
The pie chart shows clearly that almost half of all customers churning are related to other competitors
5. Meanwhile, the competitors launched aggressive promos in certain states, and it’s needed to analyze how those promos is impacting our customers
A map chart is used to visualized the number of churned customers and their percentage of total customers in each state
The map show that the state of California has abnormally high churn rate (>60%)
6. The next step is to dig dipper in the analysis and it’s a good way to categorize the data we have and create a metadata table to ease the process of the analysis and help in specifying different analysis dimensions
7. According to the findings in the previous step, it is obvious that we need to investigate more on the demographic dimension of our customer data. A new calculated column “demographics” is created to categorize the age of our customers to (Senior, Under-30 & Other) using nested-if function.
8. Analyzing churn customers’ age prevail that senior customers tend to churn more often, that indicate that customer age analysis can lead to more insight about churning. By Binning the customer age column into groups of 5 years.
It can be seen that the high churn rate in senior customers is mainly derived by the low customer number in this age
9.Next we will examine customers with different contract periods into Monthly & Yearly contract category using “Switch function” to identify how the period of contracts affect churn rate.
The graph shows the monthly subscription customers tend to churn more than other long contract customers
10.International call activity of customers are analyzed for churn rates.
The graph shows that California (state with highest churn rate) also has 72% of people making international calls have no call plan. Those can be potential customers. Also, the churn rate for customers who pay for international plan but don’t call internationally is very high.
To wrap up our findings, a dashboard is created to group our analysis in to three main dimensions. Age groups, Payment & Contract and Extra Charges
A. An overview dashboard that summarize the dimensions by which in the analysis was made upon.
B. Age group dashboard
C. Payments & Contract
D. Extra Charge
At the end; this dashboard highlits the main findings of our analysis that can help in making data-informed decisions