In reference to Gamma Gamma spend model, is this in any way related to Pareto/NBD, BG/NBD or BG/BB model?

The reason I ask this question is as follows:

  • I am currently in a remote intern position.
  • I've been asked to calculate the Customer lifetime value (past + future) for each customer based on monthly cohorts.
  • I can choose from P/NBD, BG/NBD or BG/BB model whatever is appropriate.

I came across the Gamma-Gamma spend model. Is this in any way associated with the above models? How?

According to this (https://segment.com/docs/guides/warehouses/how-do-i-forecast-ltv-with-sql-and-excel-for-e-commerce/), they just use average transaction value for each customer and multiply by expected conditional transactions. Is this a sufficient approach by changing individual averages to monthly cohort averages?

Topic marketing r

Category Data Science


The Gamma-Gamma spend model assumes that the expenditure of a client is independent of the transaction behavior.

Therefore, we can use this in conjunction with any CLV model. Models like Pareto/NBD and BG/NBD only predict the transaction behavior and client death (stops being a customer) independent of the spend value.

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.