Repeat Customer Lifetime Value Prediction

Predicting which customers will drive the most value, and allocating the right marketing spend where it matters
Targeting the right leads is a key part of any organization’s work, but with so many opportunities and noise presenting themselves online, it can be hard to pinpoint those that are worth the investment, and which to prioritize. This means a sub-optimal allocation of precious marking budget. Especially when it comes to understanding repeat customers, discovering their lifetime value (LTV) is a crucial step in ensuring every dollar spent on marketing comes back in the way of sales and future business.
The problem

A marketing firm has been spending furiously on campaigns and various efforts, but it has had trouble determining if its dollars are well spent and channeled in the right direction. The company has been using its historic data to try to identify those customers who are most likely to offer the highest LTV, but so far its results have been mixed. Internal data can only provide a sliver of the information needed to determine how much a customer is likely to spend over their life cycle, and which are worth investing more marketing dollars into.

The solution

The company built a repeat customer lifetime value prediction forecasting model, as well as an LTV predictor, by connecting its internal datasets to Explorium, and yielded the following indicators: 

  • Repeat customer forecasting
    • The likelihood a person will make a purchase for personal rather than business reasons
    • Individual online shopping behavior and purchase history 
    • Social media activity that shows positive attitudes to product
  • Customer lifetime value prediction
    • Alternative credit scores that can indicate purchasing potential
    • Online search queries related to the product
    • Online behavior on review sites indicating positive attitudes
    • Number of purchases made costing $100-$300 in the trailing 12 months
    • Demographic information that was extracted and identified as impactful
The results:

Better customer forecasting for higher LTV

Our customer is now able to better predict, following an initial sale, if their buyer will make another purchase, allowing them to place buyers on different tracks for marketing and nurture campaigns. Additionally, for repeat buyers, the marketing team can prioritize and place on more aggressive tracks those who are more likely to continue spending, while taking a longer, more subtle track with those whose LTV is not as high. Overall, the company saw an 18% increase in the number of repeat buyers, while reducing its cost per lead from $102 to $75.

Predict which customers will drive the most value and prioritize your spend.

Other resources you might be interested in:

Just announced! Explorium Announces $31M in Series B Funding to Accelerate Growth Read more