Systems and methods for determining customer lifetime value

A method comprising:

• storing, for each respective customer of a plurality of customers, respective customer information in a customer database of a retailer, the respective customer information for each respective customer of the plurality of customers comprising (1) demographic information of the respective customer, (2) online interaction information of the respective customer, and (3) transaction information comprising online store transaction information and offline store transaction information of the respective customer;
• determining, from the respective customer information in the customer database, whether each respective customer of the plurality of customers had (1) a respective online store transaction with the retailer, (2) a respective offline store transaction with the retailer, or (3) a respective online interaction with the retailer within a first predetermined period of time;
• categorizing one or more first customers of the plurality of customers into a first customer group when the one or more first customers had (1) the respective online store transaction with the retailer, (2) the respective offline store transaction with the retailer, or (3) the respective online interaction with the retailer within the first predetermined period of time;
• categorizing one or more second customers of the plurality of customers into a second customer group when the one or more second customers did not have (1) the respective online store transaction with the retailer, (2) the respective offline store transaction with the retailer, or (3) the respective online interaction with the retailer within the first predetermined period of time;
• predicting, using a lifetime value (LTV) update model, a respective LTV for each respective customer of the one or more first customers of the first customer group by:
• predicting a respective retention probability for the respective customer of the one or more first customers using a logistic regression;
• and
• determining when the respective retention probability for the respective customer of the one or more first customers is greater than a predetermined threshold value;
• predicting, using one or more LTV decay functions, the respective LTV for each respective customer of the one or more second customers of the second customer group;
• determining an online advertisement for each respective customer of the plurality of customers based on the respective LTV, as predicted, for each respective customer of the plurality of customers;
• and
• coordinating displaying the online advertisement for at least a portion of the plurality of customers.

A system comprising:

• one or more processors;
• and
• one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform:
• storing, for each respective customer of a plurality of customers, respective customer information in a customer database of a retailer;
• determining, from the respective customer information in the customer database, whether each respective customer of the plurality of customers had a respective transaction with the retailer or a respective online interaction with the retailer within a first predetermined period of time;
• categorizing one or more first customers of the plurality of customers into a first customer group when the one or more first customers had the respective transaction with the retailer or the respective online interaction with the retailer within the first predetermined period of time;
• categorizing one or more second customers of the plurality of customers into a second customer group if the one or more second customers did not have the respective transaction with the retailer or the respective online interaction with the retailer within the first predetermined period of time;
• predicting, using a lifetime value (LTV) update model, a respective LTV for each respective customer of the one or more first customers of the first customer group by:
• predicting a respective retention probability for the respective customer of the one or more first customers using a logistic regression;
• determining when the respective retention probability for each of the one or more first customers is greater than a predetermined threshold value;
• predicting (1) a gross merchandise volume (GMV) value and (2) a number of orders for each of the one or more first customers using a random forest model if the respective retention probability for each of the one or more first customers is greater than the predetermined threshold;
• and
• predicting (1) a zero GMV value and (2) zero orders for any of the one or more first customers if the respective retention probability for the any of the one or more first customers is not greater than the predetermined threshold;
• predicting, using one or more LTV decay functions, the respective LTV for each respective customer of the one or more second customers of the second customer group;
• determining an online advertisement for each respective customer of the plurality of customers based on the respective LTV, as predicted, for each respective customer of the plurality of customers;
• and
• coordinating displaying the online advertisement for at least a portion of the plurality of customers.