CODEWITHSUNDEEP
modelpoissonmle
Energizer1
Energizer1

Reputation: 295

Do you need to exclude customers with no repeat purchases before fitting the bg/nbd model?

Do you need to exclude customers with no repeat purchases before fitting the bg/nbd model with the lifetimes package?

package: https://github.com/CamDavidsonPilon/lifetimes

I have come across many different tutorials where the bg/nbd model is fitted to RFM data created using lifetimes.utils.summary_data_from_transaction_data(). Some of the tutorials claim that you must: "exclude customers for which we have no repeat purchases, i.e. frequency or frequency_cal is 0. The Pareto/NBD and BG/NBD models we will use focus exclusively on performing calculations on customers with repeat transactions." (https://www.databricks.com/notebooks/CLV_Part_1_Customer_Lifetimes.html)

Whereas other tutorials do not perform that filtering. In addition, I cannot find any mention of the from article "Counting Your Customers” the Easy Way: An Alternative to the Pareto/NBD Model" (http://brucehardie.com/papers/018/fader_et_al_mksc_05.pdf)

Does anyone now what the correct way is?

Upvotes: 0

Views: 43

Answers (0)

Related Questions