The Customer Lifetime Value (CLV) Model will give you predictive KPIs that allow you to create audiences with attributes like high future value, high risk of churning, high historic value and a lot more. It will help you dig deep into the behavior of your users and focus on the customers who are most valuable to your business. The CLV Model must be configured, validated and trained to learn from your data and the behavior of your customers. Once activated, you will find a number of attributes in the Audience Builder that can be used to define your audiences.
The CLV Model setup is available for customers with a Customer Data Platform, in the Raptor Control Panel, under the AI Models headline.
Note: The model will typically be most effective when utilized on your buy data, but it can be used on any of your data schemes e.g., visits, add to basket, downloads etc. In such cases, the Attributes listed below will have rather different meanings - for more details, see the Non-Monetary Calculations Guide.
Buy-Events or Aggregated Orders?
For the purposes of creating a CLV, there is very little difference between using Buy-Event data or Aggregated Orders, and you can largely use whichever you have available. The only difference is that a few of the stats below may varry very slightly, if some customers have made multiple orders on the same day.
List of Customer Lifetime Value attributes
As soon as the CLV model is activated, you will find the following list of attributes when you select the have-filter in the CDP's Audience Builder.
- Repurchase probability (%): Repurchase probability represents the probability of the customer placing a new order at any time in the future. It is the opposite of churn, but churn can be calculated on the basis of repurchase probability with this formula: Churn = 100 - 'repurchase probability'
repurchase probability is a prediction by the AI model. It is based on the number of orders (Frequency), days since last order (Recency), days since first order (Time), the personal "average days between orders" for the customer and the drop out rate for the shop. The drop out rate is an internal value predicted by the model. It is shop specific and represents the ability to keep customers coming back.
For example: If a customer has a repurchase probability percentage of 75 %, her churn risk is 25 %.
- Historic value last 365 days: The sum of the value of all orders by the customer during the last 365 days.
- Historic value all time: The sum of the value of all orders by the customer
- Predicted future value next 365 days: The predicted value of the customer the next 365 days. It is based on predicted number of orders next 365 days and average order value.
- Predicted Customer Lifetime Value: The sum of historic value and future value the next 365 days for the customer.
- Predicted number of orders next 365 days: This is a prediction by the AI model and tells you how many times a customer will place an order within the next 365 days. It is based on the customer's buy frequency and the predicted alive score.
- Days since first order: Number of days since the first order by the customer.
- Days since last order: Also known as recency. Number of days since the last order by the customer.
- Number of orders: Also known as frequency. The number of orders a customer has placed. Multiple items bought on the same day are aggregated into one order.
- Average order value: Also known as monetary value. The average value of the basket. It is equal to the total historic value for the customer divided by the number of orders the customer has placed. Multiple items bought on the same day are aggregated into one order.
- Average days between orders: Is the number of days between the first and last order divided by the number purchases minus one.
For example: 3 orders in 100 days (first order on day 0, last order on day 100) equals 50 days between orders on average.
- Inactivity score: Days since the customer placed her last order divided by the average days between orders for that customer. On the day a customer places an order, this score will be 0. Until the same customer buys again and has not reached her personal buying average, the inactivity score will be between 0 and 100. If she exceeds her personal buying average, the number will be more than 100.
For example: If a customer places an order every 10 days in average, but today it is 15 days since she placed her last order, the inactivity score will be 150.
How to setup a Customer Lifetime Value Model
You will find the CLV Model setup from the menu under the headline AI Models. Go to the CLV model and click + Create new model to go to the setup page.
1. General Information
Give your model a name and description so it is easy for you to recognize it. The name (suffixed by 'CLV') will be displayed as a source in the Audience Builder and on a card on the overview page. If you have created tags on the overview page, you can add those - making it possible to filter your models on the overview page.
2. Select schema & map data
To create a data foundation for the calculations and predictions of the CLV model, you need to let the system know what data the model should be based on.
First, you must select a schema. Schemas come from the Data Manager and represent how your data is mapped into Raptor's system.
Click the '+ Create mapping'-button to open the mapping pop-up.
In step 1, you see a dropdown with a list of eligible schemas. Select the desired schema (most often, this will be a buy schema).
The CLV model is applicable for all types of schemas that have been created and populated via the Data Manager.
In step 2, you need to map your data to a CLV model schema. You have three options for doing so:
- Price & Quantity: Select this schema if your data contains both a value (most often this will be the price of a product) and a quantity (most often this will be the amount of the same product the customer bought e.g., five identical t-shirts or three packs of diapers)
- Subtotal: Select this schema if your data only contains a value (most often this will be a subtotal on your buy events)
- Other events: Select this schema if one row of your data equals one value e.g., a pageviews or visits
Select the suitable schema and click Continue, which takes you to Step 3: Map data
In step 3, you select the source of the fields you wish to map, and the fields that correspond to the fields of the CLV schema on the right (Value and/or Quantity).
Press 'Create' to save your selections and close the pop-up.
CASE: Combine CLV predictions from offline and online stores
You have the possibility to create multiple mappings in one CLV model. By clicking the '+ Create mapping'-button, you can add data from different sources to your model. If you operate both an online and a physical store, it is recommended to combine buy events from both stores. This way you can take customers who have low online activity but might buy frequently in your physical store into account and base for instance churn predictions on a full picture of customer engagement.
Here is how it looks when two mappings are combined:
In this case, we recommend you to build three CLV models:
This way you have the opportunity to build predictive audiences for both your online and offline stores, and for the people who buy from both.
Note: When combining two data sources, as in this case, the time period of the data should be approximately the same, and users should be recognizable within the CDP across the two sources.
When done with the setup, you can click 'Save as draft'. This will perform an initial training-run of the model and validate its performance. You will automatically be directed to the overview page, where your newly established model should be visible with the status 'Calculating' and shortly after, it will go to the 'Draft' mode.
The Overview Page
On the overview page, you get an overview of all your CLV models. Each of them is represented with a card containing a status, name, description and an indication of model performance.
A model can have the following statuses:
- Calculating: The model is evaluating performance by calculating predictions on the basis of the selected data fields.
- Draft: The model is done calculating and you can see a performance indication, which is either high or low. The model is ready to push into production, or you can delete it and start over.
- In production: The model is in production - running once a day - and you can use the attributes in the audience builder to define audiences based on CLV predictions.
- Failed: The model has failed - you will need to edit it and try again.
On the overview page, you can filter your models by tags, and you can edit or delete them.
Model precision is an important indication of your model's ability to provide you with precise predictions. Performance can be either high or medium. Behind this simple indication is a complex set of calculations that continuously validate the model's accuracy towards the actual data. As a general rule, the more data that is included in the dataset and thus available for the model to be trained on, the more precise results it will deliver. An example is the ability to predict buy frequency; the more times a customer has placed an order, the more precise the predicted average buy frequency is.
A model with medium precision is not an obstacle for taking it into use. The cause of medium precision lies at the data set not being sufficiently large to ensure the desired accuracy in predictions. This will improve over time as new data is added to your CDP continuously, which will only make your model more precise every day.
Push the model to production
When a model has been validated and is in draft mode, you can push it to production. Press the 'Push to production'-button, and soon after the CLV attributes will be available in the Audience Builder.
Note: When you delete a CLV model, you should also delete audiences that are based on values from the model. Otherwise these audiences will be inaccurate.
Please contact Raptor if you have questions about the CLV model setup.