Customer Analytics & CLV

Introduction In this post, I will summarize the common statistical methods to describe and predict customers’ purchase behavior in non-contractual settings. It fits probabilistic models to historical transaction records for computing customer-centric metrics of managerial interest.

Introduction In this post, we’ll continue discover the difference between the Cohort Modeling and the Extended PNBD Model with time-invariant covariates. Check here to see the previous post. Data Prepare First let’s import the transactional data, and select the customers who first purchase happened in 2017-2018.

Introduction The original Pareto-NBD Model is awesome, but it does not allow us to add any covariates. In some cases, the covariates may affect the purchase, or the attrition process, or both.

Here is some tutorial notes for “Survival Analysis in R” course. Do patients taking the new drug survive longer than others? How fast do people get a new job after getting unemployed?

Introduction In the previous posts, we talked about the theoretical part of Pareto/NBD model. This time, we will go over the CLV prediction in R. Customer lifetime value (CLV) is

Theoretical proof behind PNBD Modeling Part 1.

Theoretical proof behind PNBD Modeling Part 2.

How to predict a customers mean spending in the future?