Predictive CLV is a high impact ML business use case. CLV is a customer’s past value plus their predicted future value. The goal of predictive CLV is to predict how much monetary value a user will bring to the business in a defined future time range based on historical transactions.

By knowing CLV, you can develop positive ROI strategies and make decisions about how much money to invest in acquiring new customers and retaining existing ones to grow revenue and profit.

Once your ML model is a success, you can use the results to identify customers more likely to spend money than the others, and make them respond to your offers and discounts with a greater frequency. These customers, with higher lifetime value, are your main marketing target to increase revenue.

By using the machine learning approach to predict your customers’ value, you can prioritize your next actions, such as the following:

• Decide which customers to target with advertising to increase revenue.
• Identify which customer segments are most profitable and plan how to move customers from one segment to another.

There is a strong positive correlation between the recency, frequency, and amount of money spent on each purchase each customer makes and their CLV. Consequently, you leverage these features to in your ML model. They are defined as:

• Recency: The time between the last purchase and today.
• Frequency: The time between purchases.
• Monetary: The amount of money spent on each purchase. This amount could be the average order value or the quantity of products that the customer ordered.